Image-Text-to-Text
Safetensors
MLX
mtplx
qwen4_exp
apple-silicon
macos
speculative-decoding
multi-token-prediction
qwen
qwen3.8-flash-next
Mixture of Experts
mtp
local-ai
chat
qwen3.8
qwen3-8
qwen-3.8
local-llm
llm
8-bit precision
vision
m5-max
m3-ultra
mac-studio
opencode
claude-code
flash-next
qwen3-8-flash-next
qwen4
125b
conversational
| { | |
| "metadata": { | |
| "total_parameters": 36299458451, | |
| "total_size": 135133265912 | |
| }, | |
| "weight_map": { | |
| "language_model.lm_head.biases": "model-00037-of-00037.safetensors", | |
| "language_model.lm_head.scales": "model-00037-of-00037.safetensors", | |
| "language_model.lm_head.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.embed_tokens.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.embed_tokens.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.embed_tokens.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.hyper_connection_mixer.hc_norm.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.hyper_connection_mixer.input_mix_weight_down.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.hyper_connection_mixer.input_mix_weight_up.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.0.attn_hyper_connection.block_inject_weight.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.attn_hyper_connection.hc_norm.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.A_log": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.dt_bias": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_a.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_a.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_b.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_b.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_z.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_z.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.norm.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.out_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.out_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.gate.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.gate.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.gate.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert_gate.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert_gate.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.down_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp.switch_mlp.up_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp_hyper_connection.hc_norm.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.attn_hyper_connection.block_inject_weight.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.attn_hyper_connection.hc_norm.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.A_log": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.dt_bias": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_a.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_a.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_b.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_b.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_z.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_z.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.norm.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.out_proj.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.out_proj.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.gate.biases": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.gate.scales": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.gate.weight": "model-00001-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert_gate.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert_gate.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp_hyper_connection.hc_norm.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.conv_weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.key_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.norm_conv.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.norm_key.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.norm_query.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.ple_embedding.layer_multipliers": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.ple_embedding.ngram_heads_offsets": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.1.ple.value_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.10.attn_hyper_connection.block_inject_weight.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.attn_hyper_connection.hc_norm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.A_log": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.conv1d.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.dt_bias": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_a.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_a.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_b.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_b.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_z.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_z.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.norm.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.out_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.out_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.linear_attn.out_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.gate.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.gate.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.gate.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.down_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert.up_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert_gate.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert_gate.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.shared_expert_gate.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp_hyper_connection.hc_norm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.attn_hyper_connection.hc_norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.gate.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.gate.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.gate.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.down_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert.up_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert_gate.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert_gate.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.shared_expert_gate.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.indexer.index_qk_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.indexer.index_qk_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.indexer.index_qk_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.indexer.k_layernorm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.indexer.q_layernorm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.k_norm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.o_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.o_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.q_norm.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.biases": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.scales": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00009-of-00037.safetensors", | |
| "language_model.model.layers.12.attn_hyper_connection.block_inject_weight.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.attn_hyper_connection.hc_norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.A_log": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.conv1d.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.dt_bias": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_a.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_a.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_b.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_b.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_z.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_z.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.out_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.out_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.linear_attn.out_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.gate.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.gate.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.gate.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.down_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert.up_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert_gate.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert_gate.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.shared_expert_gate.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp_hyper_connection.hc_norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.attn_hyper_connection.block_inject_weight.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.attn_hyper_connection.hc_norm.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.A_log": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.conv1d.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.dt_bias": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_a.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_a.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_b.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_b.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_z.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_z.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.norm.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.out_proj.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.out_proj.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.linear_attn.out_proj.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.gate.biases": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.gate.scales": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.gate.weight": "model-00010-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.down_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert.up_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert_gate.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert_gate.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.shared_expert_gate.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp_hyper_connection.hc_norm.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.attn_hyper_connection.block_inject_weight.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.attn_hyper_connection.hc_norm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.A_log": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.conv1d.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.dt_bias": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_a.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_a.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_b.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_b.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_z.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_z.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.norm.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.out_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.out_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.linear_attn.out_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.gate.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.gate.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.gate.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.down_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert.up_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert_gate.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert_gate.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.shared_expert_gate.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp_hyper_connection.hc_norm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.attn_hyper_connection.block_inject_weight.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.attn_hyper_connection.hc_norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.gate.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.gate.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.gate.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.down_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert.up_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert_gate.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert_gate.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.shared_expert_gate.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp_hyper_connection.hc_norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.indexer.index_qk_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.indexer.index_qk_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.indexer.index_qk_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.indexer.k_layernorm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.indexer.q_layernorm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.k_norm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.o_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.o_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.q_norm.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.biases": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.scales": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00012-of-00037.safetensors", | |
| "language_model.model.layers.16.attn_hyper_connection.block_inject_weight.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.attn_hyper_connection.hc_norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.A_log": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.conv1d.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.dt_bias": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_a.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_a.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_b.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_b.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_z.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_z.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.out_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.out_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.linear_attn.out_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.gate.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.gate.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.gate.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.down_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert.up_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert_gate.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert_gate.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.shared_expert_gate.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp_hyper_connection.hc_norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.attn_hyper_connection.block_inject_weight.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.attn_hyper_connection.hc_norm.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.A_log": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.conv1d.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.dt_bias": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_a.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_a.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_b.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_b.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_z.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_z.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.norm.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.out_proj.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.out_proj.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.linear_attn.out_proj.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.gate.biases": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.gate.scales": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.gate.weight": "model-00013-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.down_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert.up_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert_gate.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert_gate.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.shared_expert_gate.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp_hyper_connection.hc_norm.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.attn_hyper_connection.block_inject_weight.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.attn_hyper_connection.hc_norm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.A_log": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.conv1d.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.dt_bias": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_b.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_b.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.norm.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.out_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.out_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.linear_attn.out_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.gate.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.gate.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.gate.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.down_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert.up_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert_gate.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert_gate.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.shared_expert_gate.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp_hyper_connection.hc_norm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.attn_hyper_connection.block_inject_weight.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.attn_hyper_connection.hc_norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.gate.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.gate.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.gate.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.down_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert.up_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert_gate.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert_gate.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.shared_expert_gate.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp_hyper_connection.hc_norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.indexer.index_qk_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.indexer.index_qk_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.indexer.index_qk_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.indexer.k_layernorm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.indexer.q_layernorm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.k_norm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.k_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.o_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.o_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.o_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.q_norm.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.q_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.biases": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.scales": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.19.self_attn.v_proj.weight": "model-00015-of-00037.safetensors", | |
| "language_model.model.layers.2.attn_hyper_connection.block_inject_weight.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.attn_hyper_connection.hc_norm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.A_log": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.dt_bias": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_a.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_a.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_b.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_b.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_z.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_z.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.norm.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.out_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.out_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.gate.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.gate.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.gate.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert_gate.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert_gate.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp_hyper_connection.hc_norm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.20.attn_hyper_connection.block_inject_weight.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.attn_hyper_connection.hc_norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.A_log": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.conv1d.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.dt_bias": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_a.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_a.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_b.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_b.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_z.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_z.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.out_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.out_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.linear_attn.out_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.gate.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.gate.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.gate.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.down_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert.up_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert_gate.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert_gate.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.shared_expert_gate.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp_hyper_connection.hc_norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.attn_hyper_connection.block_inject_weight.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.attn_hyper_connection.hc_norm.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.A_log": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.conv1d.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.dt_bias": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_a.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_a.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_b.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_b.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_z.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_z.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.norm.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.out_proj.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.out_proj.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.linear_attn.out_proj.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.gate.biases": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.gate.scales": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.gate.weight": "model-00016-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.down_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert.up_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert_gate.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert_gate.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.shared_expert_gate.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp_hyper_connection.hc_norm.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.attn_hyper_connection.block_inject_weight.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.attn_hyper_connection.hc_norm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.A_log": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.conv1d.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.dt_bias": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_a.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_a.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_b.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_b.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_z.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_z.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.norm.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.out_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.out_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.linear_attn.out_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.gate.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.gate.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.gate.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.down_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert.up_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert_gate.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert_gate.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.shared_expert_gate.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp_hyper_connection.hc_norm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.attn_hyper_connection.block_inject_weight.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.attn_hyper_connection.hc_norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.gate.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.gate.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.gate.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.down_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert.up_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert_gate.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert_gate.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.shared_expert_gate.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp_hyper_connection.hc_norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.indexer.index_qk_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.indexer.index_qk_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.indexer.index_qk_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.indexer.k_layernorm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.indexer.q_layernorm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.k_norm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.k_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.o_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.o_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.o_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.q_norm.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.q_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.biases": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.scales": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.23.self_attn.v_proj.weight": "model-00018-of-00037.safetensors", | |
| "language_model.model.layers.24.attn_hyper_connection.block_inject_weight.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.attn_hyper_connection.hc_norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.A_log": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.conv1d.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.dt_bias": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_a.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_a.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_b.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_b.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_z.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_z.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.out_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.out_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.linear_attn.out_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.gate.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.gate.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.gate.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.down_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert.up_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert_gate.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert_gate.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.shared_expert_gate.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp_hyper_connection.hc_norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.attn_hyper_connection.block_inject_weight.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.attn_hyper_connection.hc_norm.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.A_log": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.conv1d.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.dt_bias": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_a.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_a.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_b.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_b.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_z.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_z.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.norm.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.out_proj.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.out_proj.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.linear_attn.out_proj.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.gate.biases": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.gate.scales": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.gate.weight": "model-00019-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.down_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert.up_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert_gate.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert_gate.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.shared_expert_gate.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp_hyper_connection.hc_norm.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.attn_hyper_connection.block_inject_weight.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.attn_hyper_connection.hc_norm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.A_log": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.conv1d.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.dt_bias": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_a.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_a.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_b.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_b.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_z.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_z.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.norm.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.out_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.out_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.linear_attn.out_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.gate.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.gate.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.gate.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.down_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert.up_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert_gate.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert_gate.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.shared_expert_gate.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp_hyper_connection.hc_norm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.attn_hyper_connection.block_inject_weight.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.attn_hyper_connection.hc_norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.gate.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.gate.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.gate.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.down_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert.up_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert_gate.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert_gate.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.shared_expert_gate.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp_hyper_connection.hc_norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.indexer.index_qk_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.indexer.index_qk_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.indexer.index_qk_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.indexer.k_layernorm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.indexer.q_layernorm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.k_norm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.k_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.o_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.o_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.o_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.q_norm.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.q_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.biases": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.scales": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.27.self_attn.v_proj.weight": "model-00021-of-00037.safetensors", | |
| "language_model.model.layers.28.attn_hyper_connection.block_inject_weight.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.attn_hyper_connection.hc_norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.A_log": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.conv1d.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.dt_bias": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_b.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.out_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.out_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.linear_attn.out_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.gate.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.gate.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.gate.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.down_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert.up_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert_gate.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert_gate.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.shared_expert_gate.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp_hyper_connection.hc_norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.attn_hyper_connection.block_inject_weight.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.attn_hyper_connection.hc_norm.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.A_log": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.conv1d.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.dt_bias": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_a.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_a.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_b.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_b.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_z.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_z.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.norm.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.out_proj.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.out_proj.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.linear_attn.out_proj.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.gate.biases": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.gate.scales": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.gate.weight": "model-00022-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.down_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert.up_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert_gate.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert_gate.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.shared_expert_gate.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp_hyper_connection.hc_norm.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.3.attn_hyper_connection.block_inject_weight.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.attn_hyper_connection.hc_norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.gate.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.gate.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.gate.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.down_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert.up_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert_gate.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert_gate.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.shared_expert_gate.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp_hyper_connection.hc_norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.indexer.index_qk_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.indexer.index_qk_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.indexer.index_qk_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.indexer.k_layernorm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.indexer.q_layernorm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.k_norm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.o_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.o_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.q_norm.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.biases": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.scales": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00003-of-00037.safetensors", | |
| "language_model.model.layers.30.attn_hyper_connection.block_inject_weight.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.attn_hyper_connection.hc_norm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.A_log": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.conv1d.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.dt_bias": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_a.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_a.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_b.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_b.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_z.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_z.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.norm.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.out_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.out_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.linear_attn.out_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.gate.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.gate.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.gate.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.down_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert.up_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert_gate.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert_gate.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.shared_expert_gate.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp_hyper_connection.hc_norm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.attn_hyper_connection.block_inject_weight.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.attn_hyper_connection.hc_norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.gate.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.gate.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.gate.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.down_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert.up_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert_gate.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert_gate.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.shared_expert_gate.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp_hyper_connection.hc_norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.indexer.index_qk_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.indexer.index_qk_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.indexer.index_qk_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.indexer.k_layernorm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.indexer.q_layernorm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.k_norm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.k_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.o_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.o_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.o_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.q_norm.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.q_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.biases": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.scales": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.31.self_attn.v_proj.weight": "model-00024-of-00037.safetensors", | |
| "language_model.model.layers.32.attn_hyper_connection.block_inject_weight.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.attn_hyper_connection.hc_norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.A_log": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.conv1d.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.dt_bias": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_a.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_a.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_a.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_b.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_b.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_b.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_qkv.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_z.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_z.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.in_proj_z.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.out_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.out_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.linear_attn.out_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.gate.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.gate.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.gate.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.down_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert.up_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert_gate.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert_gate.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.shared_expert_gate.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp_hyper_connection.hc_norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.attn_hyper_connection.block_inject_weight.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.attn_hyper_connection.hc_norm.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.A_log": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.conv1d.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.dt_bias": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_a.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_a.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_a.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_b.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_b.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_b.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_qkv.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_z.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_z.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.in_proj_z.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.norm.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.out_proj.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.out_proj.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.linear_attn.out_proj.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.gate.biases": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.gate.scales": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.gate.weight": "model-00025-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.down_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert.up_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert_gate.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert_gate.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.shared_expert_gate.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp_hyper_connection.hc_norm.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.attn_hyper_connection.block_inject_weight.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.attn_hyper_connection.hc_norm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.A_log": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.conv1d.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.dt_bias": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_a.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_a.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_a.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_b.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_b.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_b.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_qkv.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_z.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_z.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.in_proj_z.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.norm.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.out_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.out_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.linear_attn.out_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.gate.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.gate.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.gate.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.down_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert.up_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert_gate.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert_gate.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.shared_expert_gate.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp_hyper_connection.hc_norm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.attn_hyper_connection.block_inject_weight.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.attn_hyper_connection.hc_norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.gate.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.gate.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.gate.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.down_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert.up_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert_gate.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert_gate.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.shared_expert_gate.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp_hyper_connection.hc_norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.indexer.index_qk_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.indexer.index_qk_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.indexer.index_qk_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.indexer.k_layernorm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.indexer.q_layernorm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.k_norm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.k_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.o_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.o_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.o_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.q_norm.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.q_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.biases": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.scales": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.35.self_attn.v_proj.weight": "model-00027-of-00037.safetensors", | |
| "language_model.model.layers.36.attn_hyper_connection.block_inject_weight.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.attn_hyper_connection.hc_norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.A_log": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.conv1d.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.dt_bias": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_a.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_a.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_a.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_b.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_b.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_b.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_qkv.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_z.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_z.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.in_proj_z.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.out_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.out_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.linear_attn.out_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.gate.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.gate.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.gate.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.down_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert.up_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert_gate.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert_gate.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.shared_expert_gate.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp_hyper_connection.hc_norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.attn_hyper_connection.block_inject_weight.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.attn_hyper_connection.hc_norm.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.A_log": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.conv1d.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.dt_bias": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_a.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_a.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_a.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_b.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_b.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_b.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_qkv.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_z.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_z.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.in_proj_z.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.norm.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.out_proj.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.out_proj.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.linear_attn.out_proj.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.gate.biases": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.gate.scales": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.gate.weight": "model-00028-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.down_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert.up_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert_gate.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert_gate.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.shared_expert_gate.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp_hyper_connection.hc_norm.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.attn_hyper_connection.block_inject_weight.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.attn_hyper_connection.hc_norm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.A_log": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.conv1d.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.dt_bias": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_a.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_a.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_a.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_b.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_b.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_b.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_qkv.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_z.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_z.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.in_proj_z.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.norm.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.out_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.out_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.linear_attn.out_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.gate.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.gate.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.gate.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.down_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert.up_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert_gate.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert_gate.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.shared_expert_gate.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.biases": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.scales": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp_hyper_connection.hc_norm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.attn_hyper_connection.block_inject_weight.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.attn_hyper_connection.hc_norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.gate.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.gate.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.gate.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.down_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert.up_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert_gate.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert_gate.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.shared_expert_gate.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp_hyper_connection.hc_norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.indexer.index_qk_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.indexer.index_qk_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.indexer.index_qk_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.indexer.k_layernorm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.indexer.q_layernorm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.k_norm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.k_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.o_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.o_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.o_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.q_norm.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.q_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.biases": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.scales": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.39.self_attn.v_proj.weight": "model-00030-of-00037.safetensors", | |
| "language_model.model.layers.4.attn_hyper_connection.block_inject_weight.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.attn_hyper_connection.hc_norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.A_log": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.dt_bias": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_a.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_a.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_b.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_b.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_z.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_z.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.out_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.out_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.linear_attn.out_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.gate.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.gate.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.gate.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.down_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert.up_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert_gate.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert_gate.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.shared_expert_gate.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp_hyper_connection.hc_norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.40.attn_hyper_connection.block_inject_weight.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.attn_hyper_connection.hc_norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.A_log": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.conv1d.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.dt_bias": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_a.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_a.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_a.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_b.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_b.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_b.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_qkv.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_qkv.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_qkv.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_z.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_z.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.in_proj_z.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.out_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.out_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.linear_attn.out_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.gate.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.gate.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.gate.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.down_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.down_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.down_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.gate_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.gate_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.gate_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.up_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.up_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert.up_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert_gate.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert_gate.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.shared_expert_gate.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp_hyper_connection.hc_norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.attn_hyper_connection.block_inject_weight.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.attn_hyper_connection.hc_norm.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.A_log": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.conv1d.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.dt_bias": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_a.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_a.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_a.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_b.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_b.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_b.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_qkv.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_qkv.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_qkv.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_z.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_z.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.in_proj_z.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.norm.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.out_proj.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.out_proj.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.linear_attn.out_proj.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.gate.biases": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.gate.scales": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.gate.weight": "model-00031-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.down_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.down_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.down_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.gate_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.gate_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.gate_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.up_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.up_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert.up_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert_gate.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert_gate.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.shared_expert_gate.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp_hyper_connection.hc_norm.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.attn_hyper_connection.block_inject_weight.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.attn_hyper_connection.hc_norm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.A_log": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.conv1d.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.dt_bias": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_a.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_a.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_a.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_b.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_b.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_b.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_qkv.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_qkv.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_qkv.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_z.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_z.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.in_proj_z.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.norm.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.out_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.out_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.linear_attn.out_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.gate.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.gate.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.gate.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.down_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.down_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.down_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.gate_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.gate_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.gate_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.up_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.up_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert.up_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert_gate.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert_gate.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.shared_expert_gate.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.biases": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.scales": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp_hyper_connection.hc_norm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.attn_hyper_connection.block_inject_weight.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.attn_hyper_connection.hc_norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.gate.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.gate.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.gate.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.down_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.down_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.down_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.gate_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.gate_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.gate_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.up_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.up_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert.up_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert_gate.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert_gate.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.shared_expert_gate.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp_hyper_connection.hc_norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.indexer.index_qk_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.indexer.index_qk_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.indexer.index_qk_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.indexer.k_layernorm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.indexer.q_layernorm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.k_norm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.k_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.k_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.k_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.o_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.o_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.o_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.q_norm.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.q_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.q_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.q_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.v_proj.biases": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.v_proj.scales": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.43.self_attn.v_proj.weight": "model-00033-of-00037.safetensors", | |
| "language_model.model.layers.44.attn_hyper_connection.block_inject_weight.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.attn_hyper_connection.hc_norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.A_log": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.conv1d.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.dt_bias": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_a.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_a.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_a.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_b.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_b.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_b.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_qkv.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_qkv.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_qkv.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_z.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_z.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.in_proj_z.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.out_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.out_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.linear_attn.out_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.gate.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.gate.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.gate.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.down_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.down_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.down_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.gate_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.gate_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.gate_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.up_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.up_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert.up_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert_gate.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert_gate.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.shared_expert_gate.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp_hyper_connection.hc_norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.attn_hyper_connection.block_inject_weight.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.attn_hyper_connection.hc_norm.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.A_log": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.conv1d.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.dt_bias": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_a.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_a.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_a.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_b.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_b.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_b.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_qkv.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_qkv.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_qkv.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_z.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_z.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.in_proj_z.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.norm.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.out_proj.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.out_proj.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.linear_attn.out_proj.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.gate.biases": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.gate.scales": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.gate.weight": "model-00034-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.down_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.down_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.down_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.gate_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.gate_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.gate_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.up_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.up_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert.up_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert_gate.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert_gate.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.shared_expert_gate.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp_hyper_connection.hc_norm.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.attn_hyper_connection.block_inject_weight.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.attn_hyper_connection.hc_norm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.A_log": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.conv1d.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.dt_bias": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_a.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_a.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_a.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_b.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_b.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_b.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_qkv.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_qkv.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_qkv.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_z.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_z.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.in_proj_z.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.norm.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.out_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.out_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.linear_attn.out_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.gate.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.gate.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.gate.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.down_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.down_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.down_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.gate_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.gate_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.gate_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.up_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.up_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert.up_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert_gate.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert_gate.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.shared_expert_gate.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.down_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.biases": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.scales": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp.switch_mlp.up_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp_hyper_connection.hc_norm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.attn_hyper_connection.block_inject_weight.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.attn_hyper_connection.hc_norm.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.gate.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.gate.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.gate.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.down_proj.biases": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.down_proj.scales": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.down_proj.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.gate_proj.biases": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.gate_proj.scales": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.gate_proj.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.up_proj.biases": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.up_proj.scales": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert.up_proj.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert_gate.biases": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert_gate.scales": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.shared_expert_gate.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.biases": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.scales": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.down_proj.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp.switch_mlp.up_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp_hyper_connection.hc_norm.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.weight": "model-00037-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.indexer.index_qk_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.indexer.index_qk_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.indexer.index_qk_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.indexer.k_layernorm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.indexer.q_layernorm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.k_norm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.k_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.k_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.k_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.o_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.o_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.o_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.q_norm.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.q_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.q_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.q_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.v_proj.biases": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.v_proj.scales": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.47.self_attn.v_proj.weight": "model-00036-of-00037.safetensors", | |
| "language_model.model.layers.5.attn_hyper_connection.block_inject_weight.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.attn_hyper_connection.hc_norm.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.A_log": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.conv1d.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.dt_bias": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_a.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_a.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_b.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_b.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_z.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_z.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.norm.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.out_proj.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.out_proj.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.linear_attn.out_proj.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.gate.biases": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.gate.scales": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.gate.weight": "model-00004-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.down_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert.up_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert_gate.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert_gate.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.shared_expert_gate.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp_hyper_connection.hc_norm.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.attn_hyper_connection.block_inject_weight.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.attn_hyper_connection.hc_norm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.A_log": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.conv1d.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.dt_bias": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_a.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_a.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_b.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_b.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_z.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_z.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.norm.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.out_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.out_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.linear_attn.out_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.gate.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.gate.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.gate.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.down_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert.up_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert_gate.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert_gate.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.shared_expert_gate.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp_hyper_connection.hc_norm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.attn_hyper_connection.block_inject_weight.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.attn_hyper_connection.hc_norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.gate.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.gate.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.gate.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.down_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert.up_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert_gate.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert_gate.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.shared_expert_gate.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp_hyper_connection.hc_norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.indexer.index_qk_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.indexer.index_qk_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.indexer.index_qk_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.indexer.k_layernorm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.indexer.q_layernorm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.k_norm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.o_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.o_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.q_norm.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.biases": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.scales": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00006-of-00037.safetensors", | |
| "language_model.model.layers.8.attn_hyper_connection.block_inject_weight.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.attn_hyper_connection.hc_norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.A_log": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.conv1d.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.dt_bias": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_a.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_b.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.out_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.out_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.linear_attn.out_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.gate.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.gate.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.gate.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.down_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert.up_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert_gate.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert_gate.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.shared_expert_gate.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp_hyper_connection.hc_norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.attn_hyper_connection.block_inject_weight.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.attn_hyper_connection.hc_norm.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.A_log": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.conv1d.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.dt_bias": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_a.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_a.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_b.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_b.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_z.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_z.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.norm.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.out_proj.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.out_proj.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.linear_attn.out_proj.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.gate.biases": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.gate.scales": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.gate.weight": "model-00007-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.down_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert.up_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert_gate.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert_gate.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.shared_expert_gate.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp_hyper_connection.hc_norm.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.weight": "model-00008-of-00037.safetensors", | |
| "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.weight": "model-00008-of-00037.safetensors", | |
| "vision_tower.blocks.0.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.0.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.0.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.0.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.0.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.0.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.0.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.1.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.1.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.10.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.10.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.11.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.11.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.12.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.12.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.13.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.13.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.14.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.14.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.15.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.15.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.16.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.16.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.17.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.17.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.18.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.18.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.19.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.19.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.2.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.2.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.20.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.20.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.21.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.21.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.22.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.22.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.23.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.23.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.24.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.24.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.25.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.25.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.26.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.26.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.3.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.3.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.4.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.4.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.5.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.5.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.6.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.6.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.7.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.7.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.8.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.8.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.attn.proj.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.attn.proj.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.attn.qkv.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.attn.qkv.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.mlp.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.mlp.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.mlp.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.mlp.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.norm1.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.norm1.weight": "model-vision.safetensors", | |
| "vision_tower.blocks.9.norm2.bias": "model-vision.safetensors", | |
| "vision_tower.blocks.9.norm2.weight": "model-vision.safetensors", | |
| "vision_tower.merger.linear_fc1.bias": "model-vision.safetensors", | |
| "vision_tower.merger.linear_fc1.weight": "model-vision.safetensors", | |
| "vision_tower.merger.linear_fc2.bias": "model-vision.safetensors", | |
| "vision_tower.merger.linear_fc2.weight": "model-vision.safetensors", | |
| "vision_tower.merger.norm.bias": "model-vision.safetensors", | |
| "vision_tower.merger.norm.weight": "model-vision.safetensors", | |
| "vision_tower.patch_embed.proj.bias": "model-vision.safetensors", | |
| "vision_tower.patch_embed.proj.weight": "model-vision.safetensors", | |
| "vision_tower.pos_embed.weight": "model-vision.safetensors" | |
| } | |
| } | |