| { |
| "metadata": { |
| "total_size": 10993103808 |
| }, |
| "weight_map": { |
| "lm_head.weight": "model-00003-of-00003.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.0.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.1.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.10.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.11.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.12.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.12.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.13.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.14.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.15.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.16.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.17.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.18.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.19.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.2.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.20.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.21.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.22.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.23.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.24.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.25.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.post_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.pre_attn_norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.26.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", |
| "model.layers.27.post_attn_norm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.27.pre_attn_norm.weight": "model-00003-of-00003.safetensors", |
| "model.layers.27.self_attn.combine_heads.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.compress_mem_kv": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.k_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.k_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.k_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.k_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.k_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.norm.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.rotary_emb.freqs": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.to_qkv.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.to_qkv.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.to_strategy_combine.0.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.to_strategy_combine.0.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.v_compress.1.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.v_compress.1.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.v_compress.3.bias": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.v_compress.3.weight": "model-00002-of-00003.safetensors", |
| "model.layers.27.self_attn.v_intrablock_positions": "model-00002-of-00003.safetensors", |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.3.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.4.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.5.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.6.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.7.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.8.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.post_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.pre_attn_norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.combine_heads.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.compress_mem_kv": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.k_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.k_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.k_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.k_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.k_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.norm.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.rotary_emb.freqs": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.to_qkv.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.to_qkv.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.to_strategy_combine.0.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.to_strategy_combine.0.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.v_compress.1.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.v_compress.1.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.v_compress.3.bias": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.v_compress.3.weight": "model-00001-of-00003.safetensors", |
| "model.layers.9.self_attn.v_intrablock_positions": "model-00001-of-00003.safetensors", |
| "model.norm.weight": "model-00003-of-00003.safetensors" |
| } |
| } |
|
|
