Image-Text-to-Text
Transformers
Safetensors
English
Chinese
multilingual
step3p5v
text-generation
stepfun
step-5
Mixture of Experts
mixture-of-experts
agentic
coding
software-engineering
long-context
1m-context
multimodal
image
video
sparse-attention
gqa
financial-analysis
deep-research
tool-calling
parallel-tool-calling
json-schema
conversational
custom_code
| { | |
| "metadata": { | |
| "total_size": 1208684168984 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00024.safetensors", | |
| "model.embed_tokens.weight": "model-00024.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.0.mlp.down_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.mlp.up_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.g_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.k_norm.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.q_norm.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.1.mlp.down_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.mlp.up_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.g_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.k_norm.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.q_norm.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.10.moe.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.moe.gate.weight": "model-00003.safetensors", | |
| "model.layers.10.moe.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.moe.router_bias": "model-00003.safetensors", | |
| "model.layers.10.moe.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.g_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.k_norm.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.q_norm.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.share_expert.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.share_expert.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.10.share_expert.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.11.moe.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.moe.gate.weight": "model-00003.safetensors", | |
| "model.layers.11.moe.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.moe.router_bias": "model-00003.safetensors", | |
| "model.layers.11.moe.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.g_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.k_norm.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.q_norm.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_k.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_k_norm.bias": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_k_norm.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_q.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_q_norm.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_w.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.sparse_indexer_z.weight": "model-00003.safetensors", | |
| "model.layers.11.self_attn.ssmax_s": "model-00003.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.share_expert.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.share_expert.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.11.share_expert.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.12.moe.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.moe.gate.weight": "model-00004.safetensors", | |
| "model.layers.12.moe.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.moe.router_bias": "model-00004.safetensors", | |
| "model.layers.12.moe.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.g_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.k_norm.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.q_norm.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.share_expert.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.share_expert.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.12.share_expert.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.13.moe.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.moe.gate.weight": "model-00004.safetensors", | |
| "model.layers.13.moe.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.moe.router_bias": "model-00004.safetensors", | |
| "model.layers.13.moe.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.g_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.k_norm.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.q_norm.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.share_expert.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.share_expert.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.13.share_expert.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.14.moe.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.moe.gate.weight": "model-00004.safetensors", | |
| "model.layers.14.moe.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.moe.router_bias": "model-00004.safetensors", | |
| "model.layers.14.moe.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.g_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.k_norm.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.q_norm.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.share_expert.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.share_expert.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.14.share_expert.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.15.moe.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.moe.gate.weight": "model-00004.safetensors", | |
| "model.layers.15.moe.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.moe.router_bias": "model-00004.safetensors", | |
| "model.layers.15.moe.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.g_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.k_norm.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.q_norm.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_k.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_k_norm.bias": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_k_norm.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_q.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_q_norm.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_w.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.sparse_indexer_z.weight": "model-00004.safetensors", | |
| "model.layers.15.self_attn.ssmax_s": "model-00004.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.share_expert.down_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.share_expert.gate_proj.weight": "model-00004.safetensors", | |
| "model.layers.15.share_expert.up_proj.weight": "model-00004.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.16.moe.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.moe.gate.weight": "model-00005.safetensors", | |
| "model.layers.16.moe.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.moe.router_bias": "model-00005.safetensors", | |
| "model.layers.16.moe.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.g_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.k_norm.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.q_norm.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.share_expert.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.share_expert.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.16.share_expert.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.17.moe.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.moe.gate.weight": "model-00005.safetensors", | |
| "model.layers.17.moe.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.moe.router_bias": "model-00005.safetensors", | |
| "model.layers.17.moe.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.g_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.k_norm.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.q_norm.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.share_expert.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.share_expert.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.17.share_expert.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.18.moe.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.moe.gate.weight": "model-00005.safetensors", | |
| "model.layers.18.moe.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.moe.router_bias": "model-00005.safetensors", | |
| "model.layers.18.moe.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.g_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.k_norm.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.q_norm.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.share_expert.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.share_expert.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.18.share_expert.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.19.moe.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.moe.gate.weight": "model-00005.safetensors", | |
| "model.layers.19.moe.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.moe.router_bias": "model-00005.safetensors", | |
| "model.layers.19.moe.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.g_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.k_norm.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.q_norm.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_k.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_k_norm.bias": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_k_norm.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_q.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_q_norm.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_w.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.sparse_indexer_z.weight": "model-00005.safetensors", | |
| "model.layers.19.self_attn.ssmax_s": "model-00005.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.share_expert.down_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.share_expert.gate_proj.weight": "model-00005.safetensors", | |
| "model.layers.19.share_expert.up_proj.weight": "model-00005.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.2.mlp.down_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.mlp.up_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.g_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.k_norm.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.q_norm.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.20.moe.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.moe.gate.weight": "model-00006.safetensors", | |
| "model.layers.20.moe.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.moe.router_bias": "model-00006.safetensors", | |
| "model.layers.20.moe.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.g_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.k_norm.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.q_norm.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.share_expert.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.share_expert.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.20.share_expert.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.21.moe.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.moe.gate.weight": "model-00006.safetensors", | |
| "model.layers.21.moe.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.moe.router_bias": "model-00006.safetensors", | |
| "model.layers.21.moe.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.g_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.k_norm.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.q_norm.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.share_expert.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.share_expert.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.21.share_expert.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.22.moe.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.moe.gate.weight": "model-00006.safetensors", | |
| "model.layers.22.moe.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.moe.router_bias": "model-00006.safetensors", | |
| "model.layers.22.moe.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.g_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.k_norm.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.q_norm.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.share_expert.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.share_expert.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.22.share_expert.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.23.moe.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.moe.gate.weight": "model-00006.safetensors", | |
| "model.layers.23.moe.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.moe.router_bias": "model-00006.safetensors", | |
| "model.layers.23.moe.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.g_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.k_norm.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.q_norm.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_k.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_k_norm.bias": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_k_norm.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_q.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_q_norm.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_w.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.sparse_indexer_z.weight": "model-00006.safetensors", | |
| "model.layers.23.self_attn.ssmax_s": "model-00006.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.share_expert.down_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.share_expert.gate_proj.weight": "model-00006.safetensors", | |
| "model.layers.23.share_expert.up_proj.weight": "model-00006.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.24.moe.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.moe.gate.weight": "model-00007.safetensors", | |
| "model.layers.24.moe.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.moe.router_bias": "model-00007.safetensors", | |
| "model.layers.24.moe.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.g_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.k_norm.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.q_norm.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.share_expert.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.share_expert.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.24.share_expert.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.25.moe.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.moe.gate.weight": "model-00007.safetensors", | |
| "model.layers.25.moe.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.moe.router_bias": "model-00007.safetensors", | |
| "model.layers.25.moe.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.g_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.k_norm.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.q_norm.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.share_expert.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.share_expert.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.25.share_expert.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.26.moe.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.moe.gate.weight": "model-00007.safetensors", | |
| "model.layers.26.moe.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.moe.router_bias": "model-00007.safetensors", | |
| "model.layers.26.moe.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.g_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.k_norm.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.q_norm.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.share_expert.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.share_expert.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.26.share_expert.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.27.moe.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.moe.gate.weight": "model-00007.safetensors", | |
| "model.layers.27.moe.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.moe.router_bias": "model-00007.safetensors", | |
| "model.layers.27.moe.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.g_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.k_norm.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.q_norm.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_k.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_k_norm.bias": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_k_norm.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_q.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_q_norm.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_w.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.sparse_indexer_z.weight": "model-00007.safetensors", | |
| "model.layers.27.self_attn.ssmax_s": "model-00007.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.share_expert.down_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.share_expert.gate_proj.weight": "model-00007.safetensors", | |
| "model.layers.27.share_expert.up_proj.weight": "model-00007.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.28.moe.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.moe.gate.weight": "model-00008.safetensors", | |
| "model.layers.28.moe.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.moe.router_bias": "model-00008.safetensors", | |
| "model.layers.28.moe.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.g_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.k_norm.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.k_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.o_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.q_norm.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.q_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.self_attn.v_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.share_expert.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.share_expert.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.28.share_expert.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.29.moe.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.moe.gate.weight": "model-00008.safetensors", | |
| "model.layers.29.moe.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.moe.router_bias": "model-00008.safetensors", | |
| "model.layers.29.moe.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.g_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.k_norm.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.k_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.o_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.q_norm.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.q_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.self_attn.v_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.share_expert.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.share_expert.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.29.share_expert.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.3.moe.down_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.moe.gate.weight": "model-00001.safetensors", | |
| "model.layers.3.moe.gate_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.moe.router_bias": "model-00001.safetensors", | |
| "model.layers.3.moe.up_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.g_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.k_norm.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.q_norm.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_k.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_k_norm.bias": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_k_norm.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_q.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_q_norm.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_w.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.sparse_indexer_z.weight": "model-00001.safetensors", | |
| "model.layers.3.self_attn.ssmax_s": "model-00001.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.share_expert.down_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.share_expert.gate_proj.weight": "model-00001.safetensors", | |
| "model.layers.3.share_expert.up_proj.weight": "model-00001.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.30.moe.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.moe.gate.weight": "model-00008.safetensors", | |
| "model.layers.30.moe.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.moe.router_bias": "model-00008.safetensors", | |
| "model.layers.30.moe.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.g_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.k_norm.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.k_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.o_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.q_norm.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.q_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.self_attn.v_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.share_expert.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.share_expert.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.30.share_expert.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.31.moe.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.moe.gate.weight": "model-00008.safetensors", | |
| "model.layers.31.moe.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.moe.router_bias": "model-00008.safetensors", | |
| "model.layers.31.moe.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.g_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.k_norm.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.k_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.o_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.q_norm.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.q_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_k.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_k_norm.bias": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_k_norm.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_q.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_q_norm.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_w.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.sparse_indexer_z.weight": "model-00008.safetensors", | |
| "model.layers.31.self_attn.ssmax_s": "model-00008.safetensors", | |
| "model.layers.31.self_attn.v_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.share_expert.down_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.share_expert.gate_proj.weight": "model-00008.safetensors", | |
| "model.layers.31.share_expert.up_proj.weight": "model-00008.safetensors", | |
| "model.layers.32.input_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.32.moe.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.moe.gate.weight": "model-00009.safetensors", | |
| "model.layers.32.moe.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.moe.router_bias": "model-00009.safetensors", | |
| "model.layers.32.moe.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.post_attention_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.g_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.k_norm.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.k_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.o_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.q_norm.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.q_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.self_attn.v_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.share_expert.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.share_expert.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.32.share_expert.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.input_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.33.moe.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.moe.gate.weight": "model-00009.safetensors", | |
| "model.layers.33.moe.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.moe.router_bias": "model-00009.safetensors", | |
| "model.layers.33.moe.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.post_attention_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.g_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.k_norm.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.k_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.o_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.q_norm.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.q_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.self_attn.v_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.share_expert.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.share_expert.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.33.share_expert.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.input_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.34.moe.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.moe.gate.weight": "model-00009.safetensors", | |
| "model.layers.34.moe.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.moe.router_bias": "model-00009.safetensors", | |
| "model.layers.34.moe.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.post_attention_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.g_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.k_norm.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.k_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.o_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.q_norm.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.q_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.self_attn.v_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.share_expert.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.share_expert.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.34.share_expert.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.input_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.35.moe.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.moe.gate.weight": "model-00009.safetensors", | |
| "model.layers.35.moe.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.moe.router_bias": "model-00009.safetensors", | |
| "model.layers.35.moe.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.post_attention_layernorm.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.g_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.k_norm.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.k_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.o_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.q_norm.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.q_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_k.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_k_norm.bias": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_k_norm.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_q.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_q_norm.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_w.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.sparse_indexer_z.weight": "model-00009.safetensors", | |
| "model.layers.35.self_attn.ssmax_s": "model-00009.safetensors", | |
| "model.layers.35.self_attn.v_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.share_expert.down_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.share_expert.gate_proj.weight": "model-00009.safetensors", | |
| "model.layers.35.share_expert.up_proj.weight": "model-00009.safetensors", | |
| "model.layers.36.input_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.36.moe.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.moe.gate.weight": "model-00010.safetensors", | |
| "model.layers.36.moe.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.moe.router_bias": "model-00010.safetensors", | |
| "model.layers.36.moe.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.post_attention_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.g_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.k_norm.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.k_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.o_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.q_norm.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.q_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.self_attn.v_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.share_expert.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.share_expert.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.36.share_expert.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.input_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.37.moe.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.moe.gate.weight": "model-00010.safetensors", | |
| "model.layers.37.moe.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.moe.router_bias": "model-00010.safetensors", | |
| "model.layers.37.moe.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.post_attention_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.g_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.k_norm.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.k_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.o_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.q_norm.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.q_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.self_attn.v_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.share_expert.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.share_expert.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.37.share_expert.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.input_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.38.moe.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.moe.gate.weight": "model-00010.safetensors", | |
| "model.layers.38.moe.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.moe.router_bias": "model-00010.safetensors", | |
| "model.layers.38.moe.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.post_attention_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.g_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.k_norm.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.k_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.o_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.q_norm.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.q_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.self_attn.v_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.share_expert.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.share_expert.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.38.share_expert.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.input_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.39.moe.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.moe.gate.weight": "model-00010.safetensors", | |
| "model.layers.39.moe.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.moe.router_bias": "model-00010.safetensors", | |
| "model.layers.39.moe.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.post_attention_layernorm.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.g_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.k_norm.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.k_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.o_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.q_norm.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.q_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_k.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_k_norm.bias": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_k_norm.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_q.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_q_norm.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_w.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.sparse_indexer_z.weight": "model-00010.safetensors", | |
| "model.layers.39.self_attn.ssmax_s": "model-00010.safetensors", | |
| "model.layers.39.self_attn.v_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.share_expert.down_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.share_expert.gate_proj.weight": "model-00010.safetensors", | |
| "model.layers.39.share_expert.up_proj.weight": "model-00010.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.4.moe.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.moe.gate.weight": "model-00002.safetensors", | |
| "model.layers.4.moe.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.moe.router_bias": "model-00002.safetensors", | |
| "model.layers.4.moe.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.g_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.k_norm.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.q_norm.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.share_expert.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.share_expert.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.4.share_expert.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.40.input_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.40.moe.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.moe.gate.weight": "model-00011.safetensors", | |
| "model.layers.40.moe.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.moe.router_bias": "model-00011.safetensors", | |
| "model.layers.40.moe.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.post_attention_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.g_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.k_norm.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.k_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.o_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.q_norm.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.q_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.self_attn.v_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.share_expert.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.share_expert.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.40.share_expert.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.input_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.41.moe.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.moe.gate.weight": "model-00011.safetensors", | |
| "model.layers.41.moe.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.moe.router_bias": "model-00011.safetensors", | |
| "model.layers.41.moe.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.post_attention_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.g_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.k_norm.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.k_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.o_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.q_norm.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.q_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.self_attn.v_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.share_expert.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.share_expert.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.41.share_expert.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.input_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.42.moe.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.moe.gate.weight": "model-00011.safetensors", | |
| "model.layers.42.moe.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.moe.router_bias": "model-00011.safetensors", | |
| "model.layers.42.moe.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.post_attention_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.g_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.k_norm.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.k_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.o_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.q_norm.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.q_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.self_attn.v_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.share_expert.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.share_expert.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.42.share_expert.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.input_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.43.moe.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.moe.gate.weight": "model-00011.safetensors", | |
| "model.layers.43.moe.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.moe.router_bias": "model-00011.safetensors", | |
| "model.layers.43.moe.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.post_attention_layernorm.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.g_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.k_norm.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.k_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.o_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.q_norm.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.q_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_k.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_k_norm.bias": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_k_norm.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_q.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_q_norm.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_w.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.sparse_indexer_z.weight": "model-00011.safetensors", | |
| "model.layers.43.self_attn.ssmax_s": "model-00011.safetensors", | |
| "model.layers.43.self_attn.v_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.share_expert.down_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.share_expert.gate_proj.weight": "model-00011.safetensors", | |
| "model.layers.43.share_expert.up_proj.weight": "model-00011.safetensors", | |
| "model.layers.44.input_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.44.moe.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.moe.gate.weight": "model-00012.safetensors", | |
| "model.layers.44.moe.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.moe.router_bias": "model-00012.safetensors", | |
| "model.layers.44.moe.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.post_attention_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.g_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.k_norm.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.k_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.o_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.q_norm.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.q_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.self_attn.v_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.share_expert.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.share_expert.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.44.share_expert.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.input_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.45.moe.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.moe.gate.weight": "model-00012.safetensors", | |
| "model.layers.45.moe.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.moe.router_bias": "model-00012.safetensors", | |
| "model.layers.45.moe.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.post_attention_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.g_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.k_norm.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.k_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.o_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.q_norm.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.q_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.self_attn.v_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.share_expert.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.share_expert.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.45.share_expert.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.input_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.46.moe.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.moe.gate.weight": "model-00012.safetensors", | |
| "model.layers.46.moe.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.moe.router_bias": "model-00012.safetensors", | |
| "model.layers.46.moe.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.post_attention_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.g_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.k_norm.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.k_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.o_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.q_norm.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.q_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.self_attn.v_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.share_expert.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.share_expert.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.46.share_expert.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.input_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.47.moe.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.moe.gate.weight": "model-00012.safetensors", | |
| "model.layers.47.moe.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.moe.router_bias": "model-00012.safetensors", | |
| "model.layers.47.moe.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.post_attention_layernorm.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.g_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.k_norm.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.k_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.o_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.q_norm.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.q_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_k.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_k_norm.bias": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_k_norm.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_q.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_q_norm.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_w.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.sparse_indexer_z.weight": "model-00012.safetensors", | |
| "model.layers.47.self_attn.ssmax_s": "model-00012.safetensors", | |
| "model.layers.47.self_attn.v_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.share_expert.down_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.share_expert.gate_proj.weight": "model-00012.safetensors", | |
| "model.layers.47.share_expert.up_proj.weight": "model-00012.safetensors", | |
| "model.layers.48.input_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.48.moe.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.moe.gate.weight": "model-00013.safetensors", | |
| "model.layers.48.moe.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.moe.router_bias": "model-00013.safetensors", | |
| "model.layers.48.moe.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.post_attention_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.g_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.k_norm.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.k_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.o_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.q_norm.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.q_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.self_attn.v_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.share_expert.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.share_expert.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.48.share_expert.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.input_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.49.moe.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.moe.gate.weight": "model-00013.safetensors", | |
| "model.layers.49.moe.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.moe.router_bias": "model-00013.safetensors", | |
| "model.layers.49.moe.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.post_attention_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.g_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.k_norm.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.k_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.o_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.q_norm.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.q_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.self_attn.v_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.share_expert.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.share_expert.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.49.share_expert.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.5.moe.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.moe.gate.weight": "model-00002.safetensors", | |
| "model.layers.5.moe.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.moe.router_bias": "model-00002.safetensors", | |
| "model.layers.5.moe.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.g_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.k_norm.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.q_norm.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.share_expert.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.share_expert.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.5.share_expert.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.50.input_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.50.moe.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.moe.gate.weight": "model-00013.safetensors", | |
| "model.layers.50.moe.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.moe.router_bias": "model-00013.safetensors", | |
| "model.layers.50.moe.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.post_attention_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.g_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.k_norm.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.k_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.o_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.q_norm.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.q_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.self_attn.v_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.share_expert.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.share_expert.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.50.share_expert.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.input_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.51.moe.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.moe.gate.weight": "model-00013.safetensors", | |
| "model.layers.51.moe.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.moe.router_bias": "model-00013.safetensors", | |
| "model.layers.51.moe.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.post_attention_layernorm.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.g_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.k_norm.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.k_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.o_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.q_norm.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.q_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_k.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_k_norm.bias": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_k_norm.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_q.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_q_norm.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_w.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.sparse_indexer_z.weight": "model-00013.safetensors", | |
| "model.layers.51.self_attn.ssmax_s": "model-00013.safetensors", | |
| "model.layers.51.self_attn.v_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.share_expert.down_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.share_expert.gate_proj.weight": "model-00013.safetensors", | |
| "model.layers.51.share_expert.up_proj.weight": "model-00013.safetensors", | |
| "model.layers.52.input_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.52.moe.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.moe.gate.weight": "model-00014.safetensors", | |
| "model.layers.52.moe.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.moe.router_bias": "model-00014.safetensors", | |
| "model.layers.52.moe.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.post_attention_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.g_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.k_norm.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.k_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.o_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.q_norm.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.q_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.self_attn.v_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.share_expert.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.share_expert.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.52.share_expert.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.input_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.53.moe.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.moe.gate.weight": "model-00014.safetensors", | |
| "model.layers.53.moe.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.moe.router_bias": "model-00014.safetensors", | |
| "model.layers.53.moe.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.post_attention_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.g_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.k_norm.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.k_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.o_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.q_norm.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.q_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.self_attn.v_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.share_expert.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.share_expert.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.53.share_expert.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.input_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.54.moe.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.moe.gate.weight": "model-00014.safetensors", | |
| "model.layers.54.moe.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.moe.router_bias": "model-00014.safetensors", | |
| "model.layers.54.moe.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.post_attention_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.g_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.k_norm.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.k_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.o_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.q_norm.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.q_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.self_attn.v_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.share_expert.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.share_expert.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.54.share_expert.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.input_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.55.moe.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.moe.gate.weight": "model-00014.safetensors", | |
| "model.layers.55.moe.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.moe.router_bias": "model-00014.safetensors", | |
| "model.layers.55.moe.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.post_attention_layernorm.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.g_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.k_norm.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.k_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.o_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.q_norm.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.q_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_k.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_k_norm.bias": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_k_norm.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_q.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_q_norm.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_w.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.sparse_indexer_z.weight": "model-00014.safetensors", | |
| "model.layers.55.self_attn.ssmax_s": "model-00014.safetensors", | |
| "model.layers.55.self_attn.v_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.share_expert.down_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.share_expert.gate_proj.weight": "model-00014.safetensors", | |
| "model.layers.55.share_expert.up_proj.weight": "model-00014.safetensors", | |
| "model.layers.56.input_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.56.moe.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.moe.gate.weight": "model-00015.safetensors", | |
| "model.layers.56.moe.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.moe.router_bias": "model-00015.safetensors", | |
| "model.layers.56.moe.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.post_attention_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.g_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.k_norm.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.k_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.o_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.q_norm.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.q_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.self_attn.v_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.share_expert.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.share_expert.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.56.share_expert.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.input_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.57.moe.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.moe.gate.weight": "model-00015.safetensors", | |
| "model.layers.57.moe.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.moe.router_bias": "model-00015.safetensors", | |
| "model.layers.57.moe.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.post_attention_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.g_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.k_norm.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.k_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.o_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.q_norm.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.q_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.self_attn.v_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.share_expert.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.share_expert.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.57.share_expert.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.input_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.58.moe.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.moe.gate.weight": "model-00015.safetensors", | |
| "model.layers.58.moe.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.moe.router_bias": "model-00015.safetensors", | |
| "model.layers.58.moe.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.post_attention_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.g_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.k_norm.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.k_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.o_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.q_norm.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.q_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.self_attn.v_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.share_expert.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.share_expert.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.58.share_expert.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.input_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.59.moe.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.moe.gate.weight": "model-00015.safetensors", | |
| "model.layers.59.moe.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.moe.router_bias": "model-00015.safetensors", | |
| "model.layers.59.moe.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.post_attention_layernorm.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.g_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.k_norm.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.k_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.o_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.q_norm.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.q_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_k.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_k_norm.bias": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_k_norm.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_q.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_q_norm.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_w.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.sparse_indexer_z.weight": "model-00015.safetensors", | |
| "model.layers.59.self_attn.ssmax_s": "model-00015.safetensors", | |
| "model.layers.59.self_attn.v_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.share_expert.down_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.share_expert.gate_proj.weight": "model-00015.safetensors", | |
| "model.layers.59.share_expert.up_proj.weight": "model-00015.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.6.moe.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.moe.gate.weight": "model-00002.safetensors", | |
| "model.layers.6.moe.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.moe.router_bias": "model-00002.safetensors", | |
| "model.layers.6.moe.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.g_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.k_norm.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.q_norm.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.share_expert.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.share_expert.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.6.share_expert.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.60.input_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.60.moe.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.moe.gate.weight": "model-00016.safetensors", | |
| "model.layers.60.moe.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.moe.router_bias": "model-00016.safetensors", | |
| "model.layers.60.moe.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.post_attention_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.g_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.k_norm.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.k_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.o_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.q_norm.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.q_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.self_attn.v_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.share_expert.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.share_expert.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.60.share_expert.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.input_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.61.moe.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.moe.gate.weight": "model-00016.safetensors", | |
| "model.layers.61.moe.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.moe.router_bias": "model-00016.safetensors", | |
| "model.layers.61.moe.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.post_attention_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.g_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.k_norm.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.k_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.o_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.q_norm.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.q_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.self_attn.v_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.share_expert.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.share_expert.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.61.share_expert.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.input_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.62.moe.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.moe.gate.weight": "model-00016.safetensors", | |
| "model.layers.62.moe.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.moe.router_bias": "model-00016.safetensors", | |
| "model.layers.62.moe.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.post_attention_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.g_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.k_norm.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.k_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.o_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.q_norm.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.q_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.self_attn.v_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.share_expert.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.share_expert.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.62.share_expert.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.input_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.63.moe.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.moe.gate.weight": "model-00016.safetensors", | |
| "model.layers.63.moe.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.moe.router_bias": "model-00016.safetensors", | |
| "model.layers.63.moe.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.post_attention_layernorm.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.g_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.k_norm.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.k_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.o_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.q_norm.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.q_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_k.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_k_norm.bias": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_k_norm.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_q.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_q_norm.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_w.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.sparse_indexer_z.weight": "model-00016.safetensors", | |
| "model.layers.63.self_attn.ssmax_s": "model-00016.safetensors", | |
| "model.layers.63.self_attn.v_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.share_expert.down_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.share_expert.gate_proj.weight": "model-00016.safetensors", | |
| "model.layers.63.share_expert.up_proj.weight": "model-00016.safetensors", | |
| "model.layers.64.input_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.64.moe.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.moe.gate.weight": "model-00017.safetensors", | |
| "model.layers.64.moe.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.moe.router_bias": "model-00017.safetensors", | |
| "model.layers.64.moe.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.post_attention_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.g_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.k_norm.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.k_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.o_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.q_norm.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.q_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.self_attn.v_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.share_expert.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.share_expert.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.64.share_expert.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.input_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.65.moe.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.moe.gate.weight": "model-00017.safetensors", | |
| "model.layers.65.moe.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.moe.router_bias": "model-00017.safetensors", | |
| "model.layers.65.moe.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.post_attention_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.g_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.k_norm.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.k_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.o_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.q_norm.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.q_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.self_attn.v_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.share_expert.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.share_expert.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.65.share_expert.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.input_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.66.moe.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.moe.gate.weight": "model-00017.safetensors", | |
| "model.layers.66.moe.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.moe.router_bias": "model-00017.safetensors", | |
| "model.layers.66.moe.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.post_attention_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.g_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.k_norm.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.k_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.o_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.q_norm.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.q_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.self_attn.v_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.share_expert.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.share_expert.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.66.share_expert.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.input_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.67.moe.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.moe.gate.weight": "model-00017.safetensors", | |
| "model.layers.67.moe.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.moe.router_bias": "model-00017.safetensors", | |
| "model.layers.67.moe.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.post_attention_layernorm.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.g_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.k_norm.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.k_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.o_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.q_norm.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.q_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_k.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_k_norm.bias": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_k_norm.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_q.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_q_norm.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_w.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.sparse_indexer_z.weight": "model-00017.safetensors", | |
| "model.layers.67.self_attn.ssmax_s": "model-00017.safetensors", | |
| "model.layers.67.self_attn.v_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.share_expert.down_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.share_expert.gate_proj.weight": "model-00017.safetensors", | |
| "model.layers.67.share_expert.up_proj.weight": "model-00017.safetensors", | |
| "model.layers.68.input_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.68.moe.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.moe.gate.weight": "model-00018.safetensors", | |
| "model.layers.68.moe.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.moe.router_bias": "model-00018.safetensors", | |
| "model.layers.68.moe.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.post_attention_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.g_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.k_norm.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.k_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.o_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.q_norm.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.q_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.self_attn.v_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.share_expert.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.share_expert.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.68.share_expert.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.input_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.69.moe.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.moe.gate.weight": "model-00018.safetensors", | |
| "model.layers.69.moe.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.moe.router_bias": "model-00018.safetensors", | |
| "model.layers.69.moe.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.post_attention_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.g_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.k_norm.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.k_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.o_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.q_norm.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.q_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.self_attn.v_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.share_expert.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.share_expert.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.69.share_expert.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.7.moe.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.moe.gate.weight": "model-00002.safetensors", | |
| "model.layers.7.moe.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.moe.router_bias": "model-00002.safetensors", | |
| "model.layers.7.moe.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.g_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.k_norm.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.q_norm.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_k.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_k_norm.bias": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_k_norm.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_q.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_q_norm.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_w.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.sparse_indexer_z.weight": "model-00002.safetensors", | |
| "model.layers.7.self_attn.ssmax_s": "model-00002.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.share_expert.down_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.share_expert.gate_proj.weight": "model-00002.safetensors", | |
| "model.layers.7.share_expert.up_proj.weight": "model-00002.safetensors", | |
| "model.layers.70.input_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.70.moe.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.moe.gate.weight": "model-00018.safetensors", | |
| "model.layers.70.moe.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.moe.router_bias": "model-00018.safetensors", | |
| "model.layers.70.moe.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.post_attention_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.g_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.k_norm.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.k_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.o_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.q_norm.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.q_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.self_attn.v_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.share_expert.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.share_expert.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.70.share_expert.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.input_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.71.moe.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.moe.gate.weight": "model-00018.safetensors", | |
| "model.layers.71.moe.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.moe.router_bias": "model-00018.safetensors", | |
| "model.layers.71.moe.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.post_attention_layernorm.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.g_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.k_norm.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.k_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.o_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.q_norm.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.q_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_k.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_k_norm.bias": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_k_norm.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_q.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_q_norm.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_w.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.sparse_indexer_z.weight": "model-00018.safetensors", | |
| "model.layers.71.self_attn.ssmax_s": "model-00018.safetensors", | |
| "model.layers.71.self_attn.v_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.share_expert.down_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.share_expert.gate_proj.weight": "model-00018.safetensors", | |
| "model.layers.71.share_expert.up_proj.weight": "model-00018.safetensors", | |
| "model.layers.72.input_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.72.moe.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.moe.gate.weight": "model-00019.safetensors", | |
| "model.layers.72.moe.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.moe.router_bias": "model-00019.safetensors", | |
| "model.layers.72.moe.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.post_attention_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.g_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.k_norm.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.k_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.o_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.q_norm.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.q_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.self_attn.v_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.share_expert.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.share_expert.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.72.share_expert.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.input_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.73.moe.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.moe.gate.weight": "model-00019.safetensors", | |
| "model.layers.73.moe.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.moe.router_bias": "model-00019.safetensors", | |
| "model.layers.73.moe.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.post_attention_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.g_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.k_norm.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.k_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.o_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.q_norm.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.q_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.self_attn.v_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.share_expert.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.share_expert.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.73.share_expert.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.input_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.74.moe.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.moe.gate.weight": "model-00019.safetensors", | |
| "model.layers.74.moe.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.moe.router_bias": "model-00019.safetensors", | |
| "model.layers.74.moe.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.post_attention_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.g_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.k_norm.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.k_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.o_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.q_norm.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.q_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.self_attn.v_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.share_expert.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.share_expert.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.74.share_expert.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.input_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.75.moe.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.moe.gate.weight": "model-00019.safetensors", | |
| "model.layers.75.moe.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.moe.router_bias": "model-00019.safetensors", | |
| "model.layers.75.moe.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.post_attention_layernorm.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.g_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.k_norm.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.k_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.o_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.q_norm.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.q_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_k.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_k_norm.bias": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_k_norm.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_q.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_q_norm.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_w.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.sparse_indexer_z.weight": "model-00019.safetensors", | |
| "model.layers.75.self_attn.ssmax_s": "model-00019.safetensors", | |
| "model.layers.75.self_attn.v_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.share_expert.down_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.share_expert.gate_proj.weight": "model-00019.safetensors", | |
| "model.layers.75.share_expert.up_proj.weight": "model-00019.safetensors", | |
| "model.layers.76.input_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.76.moe.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.moe.gate.weight": "model-00020.safetensors", | |
| "model.layers.76.moe.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.moe.router_bias": "model-00020.safetensors", | |
| "model.layers.76.moe.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.post_attention_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.g_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.k_norm.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.k_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.o_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.q_norm.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.q_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.self_attn.v_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.share_expert.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.share_expert.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.76.share_expert.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.input_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.77.moe.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.moe.gate.weight": "model-00020.safetensors", | |
| "model.layers.77.moe.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.moe.router_bias": "model-00020.safetensors", | |
| "model.layers.77.moe.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.post_attention_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.g_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.k_norm.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.k_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.o_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.q_norm.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.q_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.self_attn.v_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.share_expert.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.share_expert.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.77.share_expert.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.input_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.78.moe.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.moe.gate.weight": "model-00020.safetensors", | |
| "model.layers.78.moe.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.moe.router_bias": "model-00020.safetensors", | |
| "model.layers.78.moe.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.post_attention_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.g_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.k_norm.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.k_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.o_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.q_norm.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.q_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.self_attn.v_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.share_expert.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.share_expert.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.78.share_expert.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.input_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.79.moe.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.moe.gate.weight": "model-00020.safetensors", | |
| "model.layers.79.moe.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.moe.router_bias": "model-00020.safetensors", | |
| "model.layers.79.moe.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.post_attention_layernorm.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.g_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.k_norm.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.k_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.o_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.q_norm.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.q_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_k.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_k_norm.bias": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_k_norm.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_q.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_q_norm.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_w.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.sparse_indexer_z.weight": "model-00020.safetensors", | |
| "model.layers.79.self_attn.ssmax_s": "model-00020.safetensors", | |
| "model.layers.79.self_attn.v_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.share_expert.down_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.share_expert.gate_proj.weight": "model-00020.safetensors", | |
| "model.layers.79.share_expert.up_proj.weight": "model-00020.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.8.moe.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.moe.gate.weight": "model-00003.safetensors", | |
| "model.layers.8.moe.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.moe.router_bias": "model-00003.safetensors", | |
| "model.layers.8.moe.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.g_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.k_norm.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.q_norm.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.share_expert.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.share_expert.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.8.share_expert.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.80.input_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.80.moe.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.moe.gate.weight": "model-00021.safetensors", | |
| "model.layers.80.moe.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.moe.router_bias": "model-00021.safetensors", | |
| "model.layers.80.moe.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.post_attention_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.g_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.k_norm.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.k_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.o_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.q_norm.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.q_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.self_attn.v_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.share_expert.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.share_expert.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.80.share_expert.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.input_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.81.moe.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.moe.gate.weight": "model-00021.safetensors", | |
| "model.layers.81.moe.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.moe.router_bias": "model-00021.safetensors", | |
| "model.layers.81.moe.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.post_attention_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.g_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.k_norm.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.k_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.o_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.q_norm.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.q_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.self_attn.v_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.share_expert.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.share_expert.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.81.share_expert.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.input_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.82.moe.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.moe.gate.weight": "model-00021.safetensors", | |
| "model.layers.82.moe.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.moe.router_bias": "model-00021.safetensors", | |
| "model.layers.82.moe.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.post_attention_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.g_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.k_norm.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.k_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.o_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.q_norm.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.q_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.self_attn.v_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.share_expert.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.share_expert.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.82.share_expert.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.input_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.83.moe.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.moe.gate.weight": "model-00021.safetensors", | |
| "model.layers.83.moe.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.moe.router_bias": "model-00021.safetensors", | |
| "model.layers.83.moe.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.post_attention_layernorm.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.g_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.k_norm.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.k_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.o_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.q_norm.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.q_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_k.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_k_norm.bias": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_k_norm.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_q.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_q_norm.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_w.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.sparse_indexer_z.weight": "model-00021.safetensors", | |
| "model.layers.83.self_attn.ssmax_s": "model-00021.safetensors", | |
| "model.layers.83.self_attn.v_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.share_expert.down_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.share_expert.gate_proj.weight": "model-00021.safetensors", | |
| "model.layers.83.share_expert.up_proj.weight": "model-00021.safetensors", | |
| "model.layers.84.input_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.84.moe.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.moe.gate.weight": "model-00022.safetensors", | |
| "model.layers.84.moe.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.moe.router_bias": "model-00022.safetensors", | |
| "model.layers.84.moe.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.post_attention_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.g_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.k_norm.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.k_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.o_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.q_norm.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.q_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.self_attn.v_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.share_expert.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.share_expert.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.84.share_expert.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.input_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.85.moe.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.moe.gate.weight": "model-00022.safetensors", | |
| "model.layers.85.moe.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.moe.router_bias": "model-00022.safetensors", | |
| "model.layers.85.moe.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.post_attention_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.g_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.k_norm.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.k_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.o_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.q_norm.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.q_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.self_attn.v_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.share_expert.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.share_expert.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.85.share_expert.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.input_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.86.moe.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.moe.gate.weight": "model-00022.safetensors", | |
| "model.layers.86.moe.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.moe.router_bias": "model-00022.safetensors", | |
| "model.layers.86.moe.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.post_attention_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.g_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.k_norm.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.k_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.o_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.q_norm.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.q_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.self_attn.v_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.share_expert.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.share_expert.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.86.share_expert.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.input_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.87.moe.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.moe.gate.weight": "model-00022.safetensors", | |
| "model.layers.87.moe.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.moe.router_bias": "model-00022.safetensors", | |
| "model.layers.87.moe.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.post_attention_layernorm.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.g_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.k_norm.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.k_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.o_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.q_norm.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.q_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_k.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_k_norm.bias": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_k_norm.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_q.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_q_norm.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_w.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.sparse_indexer_z.weight": "model-00022.safetensors", | |
| "model.layers.87.self_attn.ssmax_s": "model-00022.safetensors", | |
| "model.layers.87.self_attn.v_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.share_expert.down_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.share_expert.gate_proj.weight": "model-00022.safetensors", | |
| "model.layers.87.share_expert.up_proj.weight": "model-00022.safetensors", | |
| "model.layers.88.input_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.88.moe.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.moe.gate.weight": "model-00023.safetensors", | |
| "model.layers.88.moe.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.moe.router_bias": "model-00023.safetensors", | |
| "model.layers.88.moe.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.post_attention_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.g_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.k_norm.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.k_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.o_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.q_norm.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.q_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.self_attn.v_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.share_expert.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.share_expert.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.88.share_expert.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.input_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.89.moe.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.moe.gate.weight": "model-00023.safetensors", | |
| "model.layers.89.moe.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.moe.router_bias": "model-00023.safetensors", | |
| "model.layers.89.moe.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.post_attention_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.g_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.k_norm.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.k_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.o_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.q_norm.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.q_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.self_attn.v_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.share_expert.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.share_expert.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.89.share_expert.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.9.moe.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.moe.gate.weight": "model-00003.safetensors", | |
| "model.layers.9.moe.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.moe.router_bias": "model-00003.safetensors", | |
| "model.layers.9.moe.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.g_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.k_norm.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.q_norm.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.share_expert.down_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.share_expert.gate_proj.weight": "model-00003.safetensors", | |
| "model.layers.9.share_expert.up_proj.weight": "model-00003.safetensors", | |
| "model.layers.90.input_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.90.moe.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.moe.gate.weight": "model-00023.safetensors", | |
| "model.layers.90.moe.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.moe.router_bias": "model-00023.safetensors", | |
| "model.layers.90.moe.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.post_attention_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.g_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.k_norm.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.k_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.o_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.q_norm.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.q_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.self_attn.v_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.share_expert.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.share_expert.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.90.share_expert.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.input_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.91.mlp.down_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.mlp.gate_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.mlp.up_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.post_attention_layernorm.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.g_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.k_norm.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.k_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.o_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.q_norm.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.q_proj.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_k.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_k_norm.bias": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_k_norm.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_q.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_q_norm.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_w.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.sparse_indexer_z.weight": "model-00023.safetensors", | |
| "model.layers.91.self_attn.ssmax_s": "model-00023.safetensors", | |
| "model.layers.91.self_attn.v_proj.weight": "model-00023.safetensors", | |
| "model.layers.92.eh_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.enorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.hnorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.input_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.mlp.down_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.mlp.gate_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.mlp.up_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.post_attention_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.g_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.k_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.k_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.o_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.q_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.q_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.self_attn.v_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.transformer.shared_head.norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.92.transformer.shared_head.output.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.eh_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.enorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.hnorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.input_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.mlp.down_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.mlp.gate_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.mlp.up_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.post_attention_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.g_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.k_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.k_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.o_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.q_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.q_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.self_attn.v_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.transformer.shared_head.norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.93.transformer.shared_head.output.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.eh_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.enorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.hnorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.input_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.mlp.down_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.mlp.gate_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.mlp.up_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.post_attention_layernorm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.g_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.k_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.k_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.o_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.q_norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.q_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.self_attn.v_proj.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.transformer.shared_head.norm.weight": "model-mtp3-full-00001.safetensors", | |
| "model.layers.94.transformer.shared_head.output.weight": "model-mtp3-full-00001.safetensors", | |
| "model.norm.weight": "model-00024.safetensors", | |
| "vision_model.conv1.weight": "model-vit-00001.safetensors", | |
| "vision_model.ln_pre.bias": "model-vit-00001.safetensors", | |
| "vision_model.ln_pre.weight": "model-vit-00001.safetensors", | |
| "vision_model.positional_embedding": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.0.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.1.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.10.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.11.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.12.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.13.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.14.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.15.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.16.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.17.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.18.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.19.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.2.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.20.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.21.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.22.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.23.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.24.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.25.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.26.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.27.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.28.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.29.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.3.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.30.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.31.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.32.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.33.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.34.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.35.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.36.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.37.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.38.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.39.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.4.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.40.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.41.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.42.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.43.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.44.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.45.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.46.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.5.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.6.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.7.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.8.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.attn.in_proj_bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.attn.in_proj_weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.attn.out_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.attn.out_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ln_1.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ln_1.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ln_2.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ln_2.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ls_1.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.ls_2.gamma": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.mlp.c_fc.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.mlp.c_fc.weight": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.mlp.c_proj.bias": "model-vit-00001.safetensors", | |
| "vision_model.transformer.resblocks.9.mlp.c_proj.weight": "model-vit-00001.safetensors", | |
| "vision_model.vit_downsampler1.bias": "model-vit-00001.safetensors", | |
| "vision_model.vit_downsampler1.weight": "model-vit-00001.safetensors", | |
| "vision_model.vit_downsampler2.bias": "model-vit-00001.safetensors", | |
| "vision_model.vit_downsampler2.weight": "model-vit-00001.safetensors", | |
| "vit_large_projector.weight": "model-vit-00001.safetensors" | |
| } | |
| } | |