123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271 |
- {
- "metadata": {
- "total_size": 13705925200
- },
- "weight_map": {
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
- }
- }
|