+ OUTPUT_DIR=./upload-embeddinggemma_2
+ LLAMA_CPP=llama.cpp
+ DISPLAY_NAME=embeddinggemma-2
+ QUANTIZE=llama.cpp/build/bin/llama-quantize
+ python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-embeddinggemma_2-PRIMARY --outtype bf16 --outfile ./upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf --model-name embeddinggemma-2
INFO:hf-to-gguf:Loading model: model-temp-embeddinggemma_2-PRIMARY
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: EmbeddingGemma2Model
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:token_embd.weight,                 torch.bfloat16 --> BF16, shape = {512, 262144}
INFO:hf-to-gguf:output.weight,                     torch.bfloat16 --> BF16, shape = {512, 768}
INFO:hf-to-gguf:blk.0.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.0.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.0.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.0.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.0.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.0.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.0.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.0.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.0.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.0.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.0.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.0.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.0.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.0.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.0.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.1.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.1.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.1.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.1.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.1.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.1.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.1.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.1.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.1.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.1.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.1.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.1.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.1.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.1.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.1.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.10.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.10.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.10.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.10.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.10.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.10.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.10.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.10.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.10.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.10.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.10.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.10.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.10.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.10.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.10.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.10.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.11.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.11.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.11.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.11.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.11.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.11.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.11.attn_output.weight,         torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.11.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.12.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.12.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.12.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.12.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.12.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.12.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.12.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.12.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.12.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.12.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.12.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.12.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.12.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.12.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.12.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.12.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.13.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.13.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.13.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.13.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.13.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.13.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.13.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.13.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.13.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.13.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.13.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.13.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.13.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.13.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.13.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.13.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.13.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.14.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.14.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.14.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.14.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.14.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.14.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.14.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.14.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.14.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.14.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.14.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.14.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.14.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.14.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.14.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.14.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.14.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.15.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.15.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.15.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.15.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.15.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.15.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.15.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.15.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.15.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.16.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.16.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.16.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.16.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.16.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.16.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.16.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.16.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.16.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.16.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.16.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.16.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.16.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.16.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.16.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.16.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.17.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.17.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.17.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.17.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.17.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.17.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.17.attn_output.weight,         torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.17.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.17.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.18.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.18.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.18.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.18.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.18.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.18.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.18.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.18.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.18.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.18.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.18.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.18.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.18.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.18.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.18.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.18.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.18.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.19.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.19.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.19.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.19.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.19.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.19.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.19.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.19.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.19.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.2.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.2.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.2.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.2.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.2.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.2.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.2.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.2.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.2.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.2.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.2.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.2.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.2.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.2.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.2.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.20.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.20.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.20.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.20.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.20.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.20.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.20.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.20.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.20.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.20.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.20.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.20.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.20.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.20.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.20.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.20.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.21.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.21.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.21.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.21.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.21.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.21.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.21.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.21.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.21.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.21.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.21.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.21.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.21.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.21.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.21.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.21.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.21.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.22.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.22.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.22.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.22.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.22.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.22.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.22.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.22.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.22.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.22.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.22.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.22.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.22.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.22.attn_output.weight,         torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.22.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.22.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.22.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.23.attn_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.layer_output_scale.weight,  torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.23.ffn_down.weight,            torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.ffn_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.23.ffn_up.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.23.inp_gate.weight,            torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.23.proj.weight,                torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.23.post_norm.weight,           torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.post_ffw_norm.weight,       torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.ffn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.attn_k_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.attn_k.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.23.attn_output.weight,         torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.attn_q_norm.weight,         torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.attn_q.weight,              torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.23.attn_v.weight,              torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.3.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.3.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.3.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.3.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.3.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.3.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.3.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.3.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.3.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.4.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.4.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.4.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.4.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.4.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.4.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.4.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.4.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.4.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.4.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.4.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.4.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.4.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.4.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.4.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.5.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.5.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.5.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.5.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.5.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.5.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.5.attn_output.weight,          torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.5.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.5.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.6.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.6.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.6.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.6.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.6.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.6.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.6.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.6.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.6.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.6.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.6.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.6.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.6.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.6.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.6.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.6.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.7.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.7.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.7.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.7.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.7.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.7.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.7.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.7.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.7.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.8.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.8.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.8.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.8.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.8.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.8.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.8.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.8.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.8.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.8.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.8.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.8.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.8.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.8.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.8.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.8.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.9.attn_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.9.layer_output_scale.weight,   torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:blk.9.ffn_down.weight,             torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.9.ffn_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.9.ffn_up.weight,               torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.9.inp_gate.weight,             torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.9.proj.weight,                 torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.9.post_norm.weight,            torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.9.post_attention_norm.weight,  torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.9.post_ffw_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.9.ffn_norm.weight,             torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.9.attn_k_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.9.attn_k.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:blk.9.attn_output.weight,          torch.bfloat16 --> BF16, shape = {1024, 512}
INFO:hf-to-gguf:blk.9.attn_q_norm.weight,          torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.9.attn_q.weight,               torch.bfloat16 --> BF16, shape = {512, 1024}
INFO:hf-to-gguf:blk.9.attn_v.weight,               torch.bfloat16 --> BF16, shape = {512, 512}
INFO:hf-to-gguf:output_norm.weight,                torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:per_layer_model_proj.weight,       torch.bfloat16 --> BF16, shape = {512, 12288}
INFO:hf-to-gguf:per_layer_proj_norm.weight,        torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 262144
INFO:hf-to-gguf:gguf: embedding length = 512
INFO:hf-to-gguf:gguf: feed forward length = 2048
INFO:hf-to-gguf:gguf: head count = 4
INFO:hf-to-gguf:gguf: key-value head count = 2
WARNING:hf-to-gguf:Unknown RoPE type: default
INFO:hf-to-gguf:gguf: rope scaling type = NONE
INFO:hf-to-gguf:gguf: rope theta = 1000000.0
INFO:hf-to-gguf:gguf: rope theta swa = 10000.0
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: file type = 32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.context_length', overwriting it with new value 262144 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.head_count', overwriting it with new value 4 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.layer_norm_rms_epsilon', overwriting it with new value 1e-06 of type FLOAT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.key_length', overwriting it with new value 256 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.value_length', overwriting it with new value 256 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.rope.freq_base', overwriting it with new value 1000000.0 of type FLOAT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.head_count_kv', overwriting it with new value 2 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.key_length', overwriting it with new value 512 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.value_length', overwriting it with new value 512 of type UINT32
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.head_count_kv', overwriting it with new value [2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1] of type ARRAY
WARNING:gguf.gguf_writer:Duplicated key name 'gemma-embedding2.attention.sliding_window', overwriting it with new value 1024 of type UINT32
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
[transformers] You are using a model of type `embedding_gemma2` to instantiate a model of type ``. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
INFO:hf-to-gguf:Token '<|tool_call>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<tool_call|>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<|tool_response>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<tool_response|>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<|"|>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<|channel>' is set to USER_DEFINED
INFO:hf-to-gguf:Token '<channel|>' is set to USER_DEFINED
WARNING:gguf.vocab:Unknown second separator token '<bos>' in TemplateProcessing<pair>
INFO:gguf.vocab:Adding 514906 merge(s).
INFO:gguf.vocab:Setting special token type bos to 2
INFO:gguf.vocab:Setting special token type eos to 1
INFO:gguf.vocab:Setting special token type unk to 3
INFO:gguf.vocab:Setting special token type pad to 0
INFO:gguf.vocab:Setting special token type mask to 4
INFO:gguf.vocab:Setting add_bos_token to True
INFO:gguf.vocab:Setting add_eos_token to True
INFO:gguf.vocab:Setting add_sep_token to False
INFO:gguf.vocab:Setting chat_template to {%- for msg in messages if msg.get('role') == 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- for item in msg['content'] if item.get('type') == 'text' -%}{{ item['text'] }}{%- endfor -%}{%- endif -%}{%- endfor -%}{%- for msg in messages if msg.get('role') != 'system' -%}{%- if msg.get('content') is string -%}{{ msg['content'] }}{%- else -%}{%- set existing_text = msg['content'] | selectattr('type', 'equalto', 'text') | map(attribute='text') | join -%}{%- set has_manual_placeholders = ('<|image|>' in existing_text) or ('<|video|>' in existing_text) or ('<|audio|>' in existing_text) -%}{%- for item in msg['content'] -%}{%- if item.get('type') == 'text' -%}{{ item['text'] }}{%- elif not has_manual_placeholders and item.get('type') == 'image' -%}<|image|>{%- elif not has_manual_placeholders and item.get('type') == 'video' -%}<|video|>{%- elif not has_manual_placeholders and item.get('type') == 'audio' -%}<|audio|>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endfor -%}
WARNING:gguf.gguf_writer:Duplicated key name 'tokenizer.ggml.add_bos_token', overwriting it with new value True of type BOOL
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf: n_tensors = 413, total_size = 542.2M


Writing:   0%|          | 0.00/542M [00:00<?, ?byte/s]

Writing:  54%|█████▍    | 294M/542M [00:01<00:00, 293Mbyte/s]
Writing: 100%|██████████| 542M/542M [00:01<00:00, 317Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf
+ python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-embeddinggemma_2-PRIMARY --outtype bf16 --outfile ./upload-embeddinggemma_2/mmproj-embeddinggemma-2-BF16.gguf --mmproj --model-name embeddinggemma-2
INFO:hf-to-gguf:Loading model: model-temp-embeddinggemma_2-PRIMARY
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: EmbeddingGemma2Model
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:a.blk.0.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.0.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.0.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.0.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.0.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.0.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.1.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.1.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.1.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.1.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.1.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.10.ffn_up.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.10.ffn_down.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.weight,              torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.input_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.input_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.weight,            torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.output_max,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.output_min,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_post_norm_1.weight,       torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_norm_1.weight,            torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.norm_conv.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.conv_dw.weight,               torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.10.conv_pw2.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.weight,              torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.conv_pw2.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.weight,              torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.10.conv_pw1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_norm.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ln2.weight,                   torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_pre_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_k.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_k.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.per_dim_scale.weight,         torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.10.attn_out.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.weight,              torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_out.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_q.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k_rel.weight,            torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_v.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_v.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.11.ffn_up.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.11.ffn_down.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.weight,              torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.input_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.input_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.weight,            torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.output_max,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.output_min,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_post_norm_1.weight,       torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_norm_1.weight,            torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.norm_conv.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.conv_dw.weight,               torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.11.conv_pw2.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.weight,              torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.conv_pw2.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.weight,              torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.11.conv_pw1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_norm.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ln2.weight,                   torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_pre_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_k.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_k.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.per_dim_scale.weight,         torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.11.attn_out.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.weight,              torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_out.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_q.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k_rel.weight,            torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_v.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.weight,                torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_v.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.2.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.2.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.2.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.2.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.2.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.3.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.3.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.3.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.3.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.3.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.4.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.4.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.4.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.4.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.4.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.5.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.5.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.5.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.5.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.5.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.6.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.6.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.6.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.6.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.6.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.7.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.7.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.7.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.7.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.7.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.8.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.8.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.8.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.8.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.8.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.9.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.9.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.weight,               torch.bfloat16 --> BF16, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.weight,             torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.9.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.weight,               torch.bfloat16 --> BF16, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.9.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.9.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k_rel.weight,             torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.pre_encode.out.bias,                 torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:a.pre_encode.out.weight,               torch.bfloat16 --> BF16, shape = {1024, 1536}
INFO:hf-to-gguf:a.input_projection.weight,             torch.bfloat16 --> F32, shape = {1024, 1024}
INFO:hf-to-gguf:a.conv1d.0.weight,                     torch.bfloat16 --> F32, shape = {3, 3, 1, 128}
INFO:hf-to-gguf:a.conv1d.0.norm.weight,                torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.conv1d.1.weight,                     torch.bfloat16 --> F32, shape = {3, 3, 128, 32}
INFO:hf-to-gguf:a.conv1d.1.norm.weight,                torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:mm.a.input_projection.weight,          torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:mm.input_projection.weight,            torch.bfloat16 --> BF16, shape = {768, 512}
INFO:hf-to-gguf:v.blk.0.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.0.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.0.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.0.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.0.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.0.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.1.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.1.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.1.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.1.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.1.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.10.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.10.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.10.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.10.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.10.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.11.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.11.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.11.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.11.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.11.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.12.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.12.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.12.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.12.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.12.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.13.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.13.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.13.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.13.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.13.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.14.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.14.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.14.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.14.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.14.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ffn_down.weight,              torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.15.ffn_gate.weight,              torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.15.ffn_up.weight,                torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.15.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.15.attn_k.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_out.weight,              torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.15.attn_q.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_v.weight,                torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.2.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.2.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.2.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.2.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.2.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.3.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.3.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.3.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.3.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.3.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.4.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.4.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.4.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.4.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.4.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.5.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.5.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.5.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.5.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.5.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.6.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.6.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.6.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.6.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.6.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.7.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.7.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.7.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.7.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.7.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.8.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.8.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.8.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.8.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.8.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ffn_down.weight,               torch.bfloat16 --> BF16, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.9.ffn_gate.weight,               torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.9.ffn_up.weight,                 torch.bfloat16 --> BF16, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.9.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.9.attn_k.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_out.weight,               torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.9.attn_q.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_v.weight,                 torch.bfloat16 --> BF16, shape = {768, 768}
INFO:hf-to-gguf:v.patch_embd.weight,                   torch.bfloat16 --> F32, shape = {16, 16, 3, 768}
INFO:hf-to-gguf:v.position_embd.weight,                torch.bfloat16 --> F32, shape = {768, 10240, 2}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:Set model quantization version
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:upload-embeddinggemma_2/mmproj-embeddinggemma-2-BF16.gguf: n_tensors = 963, total_size = 982.0M


Writing:   0%|          | 0.00/982M [00:00<?, ?byte/s]

Writing:  35%|███▌      | 349M/982M [00:01<00:01, 347Mbyte/s]

Writing:  72%|███████▏  | 709M/982M [00:02<00:00, 354Mbyte/s]
Writing: 100%|██████████| 982M/982M [00:02<00:00, 383Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to upload-embeddinggemma_2/mmproj-embeddinggemma-2-BF16.gguf
+ llama.cpp/build/bin/llama-quantize ./upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf ./upload-embeddinggemma_2/embeddinggemma-2-Q8_0.gguf Q8_0
version: 0.6.0-dev (build 11451, commit 1e91a0b05)
built with GNU 14.2.0 for Linux x86_64
llama_quantize: quantizing './upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf' to './upload-embeddinggemma_2/embeddinggemma-2-Q8_0.gguf' as Q8_0
llama_model_loader: loaded meta data with 46 key-value pairs and 413 tensors from ./upload-embeddinggemma_2/embeddinggemma-2-BF16.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = gemma-embedding2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = embeddinggemma-2
llama_model_loader: - kv   3:                         general.size_label str              = 271M
llama_model_loader: - kv   4:                            general.license str              = apache-2.0
llama_model_loader: - kv   5:                               general.tags arr[str,13]      = ["embedding", "feature-extraction", "...
llama_model_loader: - kv   6:                          general.languages arr[str,1]       = ["multilingual"]
llama_model_loader: - kv   7:               gemma-embedding2.block_count u32              = 24
llama_model_loader: - kv   8:            gemma-embedding2.context_length u32              = 262144
llama_model_loader: - kv   9:          gemma-embedding2.embedding_length u32              = 512
llama_model_loader: - kv  10:       gemma-embedding2.feed_forward_length u32              = 2048
llama_model_loader: - kv  11:      gemma-embedding2.attention.head_count u32              = 4
llama_model_loader: - kv  12:   gemma-embedding2.attention.head_count_kv arr[i32,24]      = [2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, ...
llama_model_loader: - kv  13:            gemma-embedding2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  14:        gemma-embedding2.rope.freq_base_swa f32              = 10000.000000
llama_model_loader: - kv  15: gemma-embedding2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  16:      gemma-embedding2.attention.key_length u32              = 512
llama_model_loader: - kv  17:    gemma-embedding2.attention.value_length u32              = 512
llama_model_loader: - kv  18:                          general.file_type u32              = 32
llama_model_loader: - kv  19:  gemma-embedding2.attention.sliding_window u32              = 1024
llama_model_loader: - kv  20: gemma-embedding2.attention.shared_kv_layers u32              = 0
llama_model_loader: - kv  21: gemma-embedding2.embedding_length_per_layer_input u32              = 512
llama_model_loader: - kv  22: gemma-embedding2.attention.sliding_window_pattern arr[bool,24]     = [true, true, true, true, true, false,...
llama_model_loader: - kv  23:  gemma-embedding2.attention.key_length_swa u32              = 256
llama_model_loader: - kv  24: gemma-embedding2.attention.value_length_swa u32              = 256
llama_model_loader: - kv  25:      gemma-embedding2.rope.dimension_count u32              = 512
llama_model_loader: - kv  26:  gemma-embedding2.rope.dimension_count_swa u32              = 256
llama_model_loader: - kv  27:      gemma-embedding2.embedding_length_out u32              = 768
llama_model_loader: - kv  28:          gemma-embedding2.attention.causal bool             = false
llama_model_loader: - kv  29:              gemma-embedding2.pooling_type u32              = 1
llama_model_loader: - kv  30:               general.quantization_version u32              = 2
llama_model_loader: - kv  31:                       tokenizer.ggml.model str              = gemma4
llama_model_loader: - kv  32:                      tokenizer.ggml.tokens arr[str,262144]  = ["<pad>", "<eos>", "<bos>", "<unk>", ...
llama_model_loader: - kv  33:                      tokenizer.ggml.scores arr[f32,262144]  = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  34:                  tokenizer.ggml.token_type arr[i32,262144]  = [3, 3, 3, 3, 3, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  35:                      tokenizer.ggml.merges arr[str,514906]  = ["\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n \n", ...
llama_model_loader: - kv  36:                tokenizer.ggml.bos_token_id u32              = 2
llama_model_loader: - kv  37:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  38:            tokenizer.ggml.unknown_token_id u32              = 3
llama_model_loader: - kv  39:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  40:               tokenizer.ggml.mask_token_id u32              = 4
llama_model_loader: - kv  41:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  42:               tokenizer.ggml.add_eos_token bool             = true
llama_model_loader: - kv  43:               tokenizer.ggml.add_sep_token bool             = false
llama_model_loader: - kv  44:                    tokenizer.chat_template str              = {%- for msg in messages if msg.get('r...
llama_model_loader: - kv  45:            tokenizer.ggml.add_space_prefix bool             = false
llama_model_loader: - type  f32:  194 tensors
llama_model_loader: - type bf16:  219 tensors
[   1/ 413] output.weight                        - [   512,    768,      1,      1], type =   bf16, converting to q8_0 .. size =     0.75 MiB ->     0.40 MiB
[   2/ 413] output_norm.weight                   - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[   3/ 413] per_layer_model_proj.weight          - [   512,  12288,      1,      1], type =   bf16, size =   12.000 MiB
[   4/ 413] per_layer_proj_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[   5/ 413] token_embd.weight                    - [   512, 262144,      1,      1], type =   bf16, converting to q8_0 .. size =   256.00 MiB ->   136.00 MiB
[   6/ 413] blk.0.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[   7/ 413] blk.0.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[   8/ 413] blk.0.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[   9/ 413] blk.0.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  10/ 413] blk.0.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  11/ 413] blk.0.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  12/ 413] blk.0.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  13/ 413] blk.0.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  14/ 413] blk.0.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  15/ 413] blk.0.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  16/ 413] blk.0.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  17/ 413] blk.0.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  18/ 413] blk.0.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[  19/ 413] blk.0.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  20/ 413] blk.0.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  21/ 413] blk.0.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  22/ 413] blk.0.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  23/ 413] blk.1.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  24/ 413] blk.1.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  25/ 413] blk.1.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  26/ 413] blk.1.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  27/ 413] blk.1.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  28/ 413] blk.1.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  29/ 413] blk.1.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  30/ 413] blk.1.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  31/ 413] blk.1.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  32/ 413] blk.1.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  33/ 413] blk.1.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  34/ 413] blk.1.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  35/ 413] blk.1.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[  36/ 413] blk.1.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  37/ 413] blk.1.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  38/ 413] blk.1.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  39/ 413] blk.1.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  40/ 413] blk.2.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  41/ 413] blk.2.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  42/ 413] blk.2.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  43/ 413] blk.2.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  44/ 413] blk.2.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  45/ 413] blk.2.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  46/ 413] blk.2.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  47/ 413] blk.2.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  48/ 413] blk.2.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  49/ 413] blk.2.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  50/ 413] blk.2.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  51/ 413] blk.2.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  52/ 413] blk.2.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[  53/ 413] blk.2.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  54/ 413] blk.2.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  55/ 413] blk.2.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  56/ 413] blk.2.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  57/ 413] blk.3.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  58/ 413] blk.3.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  59/ 413] blk.3.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  60/ 413] blk.3.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  61/ 413] blk.3.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  62/ 413] blk.3.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  63/ 413] blk.3.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  64/ 413] blk.3.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  65/ 413] blk.3.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  66/ 413] blk.3.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  67/ 413] blk.3.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  68/ 413] blk.3.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  69/ 413] blk.3.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[  70/ 413] blk.3.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  71/ 413] blk.3.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  72/ 413] blk.3.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  73/ 413] blk.3.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  74/ 413] blk.4.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  75/ 413] blk.4.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  76/ 413] blk.4.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  77/ 413] blk.4.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  78/ 413] blk.4.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[  79/ 413] blk.4.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[  80/ 413] blk.4.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  81/ 413] blk.4.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  82/ 413] blk.4.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  83/ 413] blk.4.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  84/ 413] blk.4.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  85/ 413] blk.4.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  86/ 413] blk.4.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[  87/ 413] blk.4.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  88/ 413] blk.4.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  89/ 413] blk.4.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  90/ 413] blk.4.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  91/ 413] blk.5.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  92/ 413] blk.5.attn_k_norm.weight             - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  93/ 413] blk.5.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  94/ 413] blk.5.attn_output.weight             - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  95/ 413] blk.5.attn_q.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  96/ 413] blk.5.attn_q_norm.weight             - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[  97/ 413] blk.5.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[  98/ 413] blk.5.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[  99/ 413] blk.5.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 100/ 413] blk.5.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 101/ 413] blk.5.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 102/ 413] blk.5.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 103/ 413] blk.5.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 104/ 413] blk.5.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 105/ 413] blk.5.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 106/ 413] blk.5.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 107/ 413] blk.5.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 108/ 413] blk.6.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 109/ 413] blk.6.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 110/ 413] blk.6.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 111/ 413] blk.6.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 112/ 413] blk.6.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 113/ 413] blk.6.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 114/ 413] blk.6.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 115/ 413] blk.6.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 116/ 413] blk.6.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 117/ 413] blk.6.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 118/ 413] blk.6.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 119/ 413] blk.6.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 120/ 413] blk.6.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 121/ 413] blk.6.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 122/ 413] blk.6.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 123/ 413] blk.6.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 124/ 413] blk.6.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 125/ 413] blk.7.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 126/ 413] blk.7.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 127/ 413] blk.7.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 128/ 413] blk.7.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 129/ 413] blk.7.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 130/ 413] blk.7.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 131/ 413] blk.7.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 132/ 413] blk.7.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 133/ 413] blk.7.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 134/ 413] blk.7.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 135/ 413] blk.7.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 136/ 413] blk.7.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 137/ 413] blk.7.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 138/ 413] blk.7.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 139/ 413] blk.7.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 140/ 413] blk.7.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 141/ 413] blk.7.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 142/ 413] blk.8.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 143/ 413] blk.8.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 144/ 413] blk.8.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 145/ 413] blk.8.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 146/ 413] blk.8.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 147/ 413] blk.8.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 148/ 413] blk.8.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 149/ 413] blk.8.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 150/ 413] blk.8.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 151/ 413] blk.8.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 152/ 413] blk.8.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 153/ 413] blk.8.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 154/ 413] blk.8.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 155/ 413] blk.8.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 156/ 413] blk.8.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 157/ 413] blk.8.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 158/ 413] blk.8.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 159/ 413] blk.9.attn_k.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 160/ 413] blk.9.attn_k_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 161/ 413] blk.9.attn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 162/ 413] blk.9.attn_output.weight             - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 163/ 413] blk.9.attn_q.weight                  - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 164/ 413] blk.9.attn_q_norm.weight             - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 165/ 413] blk.9.attn_v.weight                  - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 166/ 413] blk.9.ffn_down.weight                - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 167/ 413] blk.9.ffn_gate.weight                - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 168/ 413] blk.9.ffn_norm.weight                - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 169/ 413] blk.9.ffn_up.weight                  - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 170/ 413] blk.9.inp_gate.weight                - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 171/ 413] blk.9.layer_output_scale.weight      - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 172/ 413] blk.9.post_attention_norm.weight     - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 173/ 413] blk.9.post_ffw_norm.weight           - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 174/ 413] blk.9.post_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 175/ 413] blk.9.proj.weight                    - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 176/ 413] blk.10.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 177/ 413] blk.10.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 178/ 413] blk.10.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 179/ 413] blk.10.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 180/ 413] blk.10.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 181/ 413] blk.10.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 182/ 413] blk.10.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 183/ 413] blk.10.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 184/ 413] blk.10.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 185/ 413] blk.10.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 186/ 413] blk.10.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 187/ 413] blk.10.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 188/ 413] blk.10.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 189/ 413] blk.10.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 190/ 413] blk.10.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 191/ 413] blk.10.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 192/ 413] blk.10.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 193/ 413] blk.11.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 194/ 413] blk.11.attn_k_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 195/ 413] blk.11.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 196/ 413] blk.11.attn_output.weight            - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 197/ 413] blk.11.attn_q.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 198/ 413] blk.11.attn_q_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 199/ 413] blk.11.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 200/ 413] blk.11.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 201/ 413] blk.11.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 202/ 413] blk.11.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 203/ 413] blk.11.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 204/ 413] blk.11.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 205/ 413] blk.11.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 206/ 413] blk.11.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 207/ 413] blk.11.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 208/ 413] blk.11.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 209/ 413] blk.11.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 210/ 413] blk.12.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 211/ 413] blk.12.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 212/ 413] blk.12.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 213/ 413] blk.12.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 214/ 413] blk.12.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 215/ 413] blk.12.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 216/ 413] blk.12.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 217/ 413] blk.12.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 218/ 413] blk.12.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 219/ 413] blk.12.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 220/ 413] blk.12.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 221/ 413] blk.12.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 222/ 413] blk.12.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 223/ 413] blk.12.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 224/ 413] blk.12.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 225/ 413] blk.12.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 226/ 413] blk.12.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 227/ 413] blk.13.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 228/ 413] blk.13.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 229/ 413] blk.13.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 230/ 413] blk.13.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 231/ 413] blk.13.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 232/ 413] blk.13.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 233/ 413] blk.13.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 234/ 413] blk.13.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 235/ 413] blk.13.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 236/ 413] blk.13.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 237/ 413] blk.13.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 238/ 413] blk.13.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 239/ 413] blk.13.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 240/ 413] blk.13.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 241/ 413] blk.13.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 242/ 413] blk.13.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 243/ 413] blk.13.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 244/ 413] blk.14.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 245/ 413] blk.14.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 246/ 413] blk.14.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 247/ 413] blk.14.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 248/ 413] blk.14.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 249/ 413] blk.14.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 250/ 413] blk.14.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 251/ 413] blk.14.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 252/ 413] blk.14.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 253/ 413] blk.14.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 254/ 413] blk.14.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 255/ 413] blk.14.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 256/ 413] blk.14.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 257/ 413] blk.14.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 258/ 413] blk.14.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 259/ 413] blk.14.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 260/ 413] blk.14.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 261/ 413] blk.15.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 262/ 413] blk.15.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 263/ 413] blk.15.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 264/ 413] blk.15.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 265/ 413] blk.15.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 266/ 413] blk.15.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 267/ 413] blk.15.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 268/ 413] blk.15.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 269/ 413] blk.15.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 270/ 413] blk.15.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 271/ 413] blk.15.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 272/ 413] blk.15.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 273/ 413] blk.15.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 274/ 413] blk.15.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 275/ 413] blk.15.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 276/ 413] blk.15.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 277/ 413] blk.15.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 278/ 413] blk.16.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 279/ 413] blk.16.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 280/ 413] blk.16.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 281/ 413] blk.16.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 282/ 413] blk.16.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 283/ 413] blk.16.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 284/ 413] blk.16.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 285/ 413] blk.16.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 286/ 413] blk.16.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 287/ 413] blk.16.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 288/ 413] blk.16.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 289/ 413] blk.16.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 290/ 413] blk.16.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 291/ 413] blk.16.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 292/ 413] blk.16.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 293/ 413] blk.16.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 294/ 413] blk.16.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 295/ 413] blk.17.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 296/ 413] blk.17.attn_k_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 297/ 413] blk.17.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 298/ 413] blk.17.attn_output.weight            - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 299/ 413] blk.17.attn_q.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 300/ 413] blk.17.attn_q_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 301/ 413] blk.17.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 302/ 413] blk.17.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 303/ 413] blk.17.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 304/ 413] blk.17.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 305/ 413] blk.17.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 306/ 413] blk.17.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 307/ 413] blk.17.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 308/ 413] blk.17.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 309/ 413] blk.17.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 310/ 413] blk.17.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 311/ 413] blk.17.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 312/ 413] blk.18.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 313/ 413] blk.18.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 314/ 413] blk.18.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 315/ 413] blk.18.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 316/ 413] blk.18.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 317/ 413] blk.18.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 318/ 413] blk.18.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 319/ 413] blk.18.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 320/ 413] blk.18.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 321/ 413] blk.18.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 322/ 413] blk.18.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 323/ 413] blk.18.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 324/ 413] blk.18.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 325/ 413] blk.18.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 326/ 413] blk.18.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 327/ 413] blk.18.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 328/ 413] blk.18.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 329/ 413] blk.19.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 330/ 413] blk.19.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 331/ 413] blk.19.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 332/ 413] blk.19.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 333/ 413] blk.19.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 334/ 413] blk.19.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 335/ 413] blk.19.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 336/ 413] blk.19.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 337/ 413] blk.19.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 338/ 413] blk.19.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 339/ 413] blk.19.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 340/ 413] blk.19.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 341/ 413] blk.19.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 342/ 413] blk.19.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 343/ 413] blk.19.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 344/ 413] blk.19.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 345/ 413] blk.19.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 346/ 413] blk.20.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 347/ 413] blk.20.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 348/ 413] blk.20.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 349/ 413] blk.20.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 350/ 413] blk.20.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 351/ 413] blk.20.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 352/ 413] blk.20.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 353/ 413] blk.20.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 354/ 413] blk.20.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 355/ 413] blk.20.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 356/ 413] blk.20.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 357/ 413] blk.20.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 358/ 413] blk.20.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 359/ 413] blk.20.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 360/ 413] blk.20.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 361/ 413] blk.20.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 362/ 413] blk.20.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 363/ 413] blk.21.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 364/ 413] blk.21.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 365/ 413] blk.21.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 366/ 413] blk.21.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 367/ 413] blk.21.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 368/ 413] blk.21.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 369/ 413] blk.21.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 370/ 413] blk.21.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 371/ 413] blk.21.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 372/ 413] blk.21.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 373/ 413] blk.21.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 374/ 413] blk.21.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 375/ 413] blk.21.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 376/ 413] blk.21.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 377/ 413] blk.21.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 378/ 413] blk.21.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 379/ 413] blk.21.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 380/ 413] blk.22.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 381/ 413] blk.22.attn_k_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 382/ 413] blk.22.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 383/ 413] blk.22.attn_output.weight            - [  1024,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 384/ 413] blk.22.attn_q.weight                 - [   512,   1024,      1,      1], type =   bf16, converting to q8_0 .. size =     1.00 MiB ->     0.53 MiB
[ 385/ 413] blk.22.attn_q_norm.weight            - [   256,      1,      1,      1], type =    f32, size =    0.001 MiB
[ 386/ 413] blk.22.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 387/ 413] blk.22.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 388/ 413] blk.22.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 389/ 413] blk.22.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 390/ 413] blk.22.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 391/ 413] blk.22.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 392/ 413] blk.22.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 393/ 413] blk.22.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 394/ 413] blk.22.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 395/ 413] blk.22.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 396/ 413] blk.22.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 397/ 413] blk.23.attn_k.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 398/ 413] blk.23.attn_k_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 399/ 413] blk.23.attn_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 400/ 413] blk.23.attn_output.weight            - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 401/ 413] blk.23.attn_q.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 402/ 413] blk.23.attn_q_norm.weight            - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 403/ 413] blk.23.attn_v.weight                 - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 404/ 413] blk.23.ffn_down.weight               - [  2048,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 405/ 413] blk.23.ffn_gate.weight               - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 406/ 413] blk.23.ffn_norm.weight               - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 407/ 413] blk.23.ffn_up.weight                 - [   512,   2048,      1,      1], type =   bf16, converting to q8_0 .. size =     2.00 MiB ->     1.06 MiB
[ 408/ 413] blk.23.inp_gate.weight               - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
[ 409/ 413] blk.23.layer_output_scale.weight     - [     1,      1,      1,      1], type =    f32, size =    0.000 MiB
[ 410/ 413] blk.23.post_attention_norm.weight    - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 411/ 413] blk.23.post_ffw_norm.weight          - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 412/ 413] blk.23.post_norm.weight              - [   512,      1,      1,      1], type =    f32, size =    0.002 MiB
[ 413/ 413] blk.23.proj.weight                   - [   512,    512,      1,      1], type =   bf16, converting to q8_0 .. size =     0.50 MiB ->     0.27 MiB
llama_model_quantize_impl: model size  =   517.04 MiB (16.00 BPW)
llama_model_quantize_impl: quant size  =   280.44 MiB (8.68 BPW)

llama_quantize: quantize time =  1855.14 ms
llama_quantize:    total time =  1855.14 ms
+ python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-embeddinggemma_2-PRIMARY --outtype q8_0 --outfile ./upload-embeddinggemma_2/mmproj-embeddinggemma-2-Q8_0.gguf --mmproj --model-name embeddinggemma-2
INFO:hf-to-gguf:Loading model: model-temp-embeddinggemma_2-PRIMARY
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: EmbeddingGemma2Model
WARNING:hf-to-gguf:Failed to load model config from model-temp-embeddinggemma_2-PRIMARY: The checkpoint you are trying to load has model type `embedding_gemma2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

You can update Transformers with the command `pip install --upgrade transformers`. If this does not work, and the checkpoint is very new, then there may not be a release version that supports this model yet. In this case, you can get the most up-to-date code by installing Transformers from source with the command `pip install git+https://github.com/huggingface/transformers.git`
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:a.blk.0.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.0.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.0.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.0.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.0.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.0.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.0.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.0.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.0.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.1.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.1.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.1.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.1.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.1.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.1.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.1.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.1.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.10.ffn_up.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.10.ffn_down.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_up_1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.input_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.input_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.weight,            torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.output_max,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_down_1.output_min,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.ffn_post_norm_1.weight,       torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ffn_norm_1.weight,            torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.norm_conv.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.conv_dw.weight,               torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.10.conv_pw2.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.conv_pw2.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw2.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.10.conv_pw1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_pw1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.conv_norm.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.ln2.weight,                   torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_pre_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.10.attn_k.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_k.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.per_dim_scale.weight,         torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.10.attn_out.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_out.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_out.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_q.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_q.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_k_rel.weight,            torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_v.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.10.attn_v.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.10.attn_v.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.11.ffn_up.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.11.ffn_down.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_up_1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.input_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.input_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.weight,            torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.output_max,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_down_1.output_min,        torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.ffn_post_norm_1.weight,       torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ffn_norm_1.weight,            torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.norm_conv.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.conv_dw.weight,               torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.11.conv_pw2.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.conv_pw2.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw2.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.11.conv_pw1.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_pw1.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.conv_norm.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.ln2.weight,                   torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_pre_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.11.attn_k.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_k.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.per_dim_scale.weight,         torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.11.attn_out.input_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.input_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_out.output_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_out.output_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_q.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_q.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_k_rel.weight,            torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_v.input_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.input_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.11.attn_v.output_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.11.attn_v.output_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.2.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.2.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.2.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.2.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.2.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.2.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.2.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.2.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.3.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.3.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.3.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.3.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.3.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.3.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.3.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.3.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.4.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.4.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.4.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.4.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.4.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.4.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.4.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.4.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.5.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.5.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.5.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.5.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.5.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.5.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.5.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.5.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.6.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.6.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.6.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.6.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.6.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.6.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.6.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.6.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.7.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.7.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.7.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.7.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.7.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.7.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.7.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.7.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.8.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.8.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.8.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.8.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.8.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.8.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.8.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.8.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.9.ffn_up.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.9.ffn_down.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_norm.weight,               torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 4096}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_up_1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.input_max,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.input_min,          torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.weight,             torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.output_max,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_down_1.output_min,         torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.ffn_post_norm_1.weight,        torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ffn_norm_1.weight,             torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.norm_conv.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.conv_dw.weight,                torch.bfloat16 --> F32, shape = {5, 1024}
INFO:hf-to-gguf:a.blk.9.conv_pw2.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.conv_pw2.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw2.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 2048}
INFO:hf-to-gguf:a.blk.9.conv_pw1.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_pw1.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.conv_norm.weight,              torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.ln2.weight,                    torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_pre_norm.weight,          torch.bfloat16 --> F32, shape = {1024}
INFO:hf-to-gguf:a.blk.9.attn_k.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_k.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.per_dim_scale.weight,          torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.blk.9.attn_out.input_max,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.input_min,            torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_out.output_max,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_out.output_min,           torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_q.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_q.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_k_rel.weight,             torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_v.input_max,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.input_min,              torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {1024, 1024}
INFO:hf-to-gguf:a.blk.9.attn_v.output_max,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.blk.9.attn_v.output_min,             torch.bfloat16 --> F32, shape = {1}
INFO:hf-to-gguf:a.pre_encode.out.bias,                 torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:a.pre_encode.out.weight,               torch.bfloat16 --> Q8_0, shape = {1024, 1536}
INFO:hf-to-gguf:a.input_projection.weight,             torch.bfloat16 --> F32, shape = {1024, 1024}
INFO:hf-to-gguf:a.conv1d.0.weight,                     torch.bfloat16 --> F32, shape = {3, 3, 1, 128}
INFO:hf-to-gguf:a.conv1d.0.norm.weight,                torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:a.conv1d.1.weight,                     torch.bfloat16 --> F32, shape = {3, 3, 128, 32}
INFO:hf-to-gguf:a.conv1d.1.norm.weight,                torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:mm.a.input_projection.weight,          torch.bfloat16 --> Q8_0, shape = {1536, 512}
INFO:hf-to-gguf:mm.input_projection.weight,            torch.bfloat16 --> Q8_0, shape = {768, 512}
INFO:hf-to-gguf:v.blk.0.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.0.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.0.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.0.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.0.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.0.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.0.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.0.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.1.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.1.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.1.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.1.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.1.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.1.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.1.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.10.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.10.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.10.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.10.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.10.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.10.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.10.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.11.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.11.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.11.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.11.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.11.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.11.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.11.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.12.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.12.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.12.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.12.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.12.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.12.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.12.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.13.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.13.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.13.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.13.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.13.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.13.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.13.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.14.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.14.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.14.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.14.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.14.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.14.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.14.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.ln1.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ffn_down.weight,              torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.15.ffn_gate.weight,              torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.15.ffn_up.weight,                torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.15.attn_post_norm.weight,        torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ffn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.ln2.weight,                   torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.15.attn_k_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.15.attn_k.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_out.weight,              torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_q_norm.weight,           torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.15.attn_q.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.15.attn_v.weight,                torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.2.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.2.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.2.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.2.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.2.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.2.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.2.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.3.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.3.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.3.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.3.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.3.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.3.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.3.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.4.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.4.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.4.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.4.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.4.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.4.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.4.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.5.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.5.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.5.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.5.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.5.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.5.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.5.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.6.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.6.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.6.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.6.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.6.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.6.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.6.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.7.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.7.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.7.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.7.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.7.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.7.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.7.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.8.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.8.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.8.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.8.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.8.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.8.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.8.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.ln1.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ffn_down.weight,               torch.bfloat16 --> Q8_0, shape = {3072, 768}
INFO:hf-to-gguf:v.blk.9.ffn_gate.weight,               torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.9.ffn_up.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 3072}
INFO:hf-to-gguf:v.blk.9.attn_post_norm.weight,         torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ffn_post_norm.weight,          torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.ln2.weight,                    torch.bfloat16 --> F32, shape = {768}
INFO:hf-to-gguf:v.blk.9.attn_k_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.9.attn_k.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_out.weight,               torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_q_norm.weight,            torch.bfloat16 --> F32, shape = {64}
INFO:hf-to-gguf:v.blk.9.attn_q.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.blk.9.attn_v.weight,                 torch.bfloat16 --> Q8_0, shape = {768, 768}
INFO:hf-to-gguf:v.patch_embd.weight,                   torch.bfloat16 --> F32, shape = {16, 16, 3, 768}
INFO:hf-to-gguf:v.position_embd.weight,                torch.bfloat16 --> F32, shape = {768, 10240, 2}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:Set model quantization version
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:upload-embeddinggemma_2/mmproj-embeddinggemma-2-Q8_0.gguf: n_tensors = 963, total_size = 554.7M


Writing:   0%|          | 0.00/555M [00:00<?, ?byte/s]

Writing:  30%|██▉       | 165M/555M [00:01<00:02, 165Mbyte/s]

Writing:  61%|██████    | 336M/555M [00:02<00:01, 168Mbyte/s]
Writing: 100%|██████████| 555M/555M [00:03<00:00, 185Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to upload-embeddinggemma_2/mmproj-embeddinggemma-2-Q8_0.gguf
+ echo embeddinggemma-2-BF16.gguf
+ echo embeddinggemma-2-Q8_0.gguf
+ echo mmproj-embeddinggemma-2-BF16.gguf
+ echo mmproj-embeddinggemma-2-Q8_0.gguf