| { | |
| "metadata": { | |
| "total_size": 6121212928 | |
| }, | |
| "weight_map": { | |
| "layer_norm_before_lm_heads.0.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.1.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.10.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.11.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.12.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.13.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.14.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.15.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.16.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.17.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.18.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.19.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.2.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.20.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.21.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.22.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.23.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.24.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.25.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.26.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.27.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.28.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.29.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.3.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.30.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.31.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.32.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.4.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.5.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.6.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.7.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.8.weight": "model-00002-of-00002.safetensors", | |
| "layer_norm_before_lm_heads.9.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.0.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.1.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.10.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.11.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.12.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.13.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.14.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.15.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.16.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.17.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.18.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.19.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.2.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.20.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.21.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.22.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.23.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.24.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.25.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.26.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.27.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.28.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.29.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.3.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.30.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.31.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.32.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.4.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.5.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.6.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.7.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.8.weight": "model-00002-of-00002.safetensors", | |
| "lm_heads.9.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.0.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.0.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.0.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.1.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.1.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.1.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.10.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.10.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.10.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.11.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.11.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.11.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.12.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.12.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.12.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.13.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.13.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.13.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.14.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.14.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.14.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.15.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.15.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.15.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.16.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.16.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.16.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.17.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.17.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.17.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.18.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.18.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.18.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.19.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.19.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.19.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.2.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.2.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.2.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.20.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.20.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.20.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.21.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.21.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.21.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.22.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.22.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.22.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.23.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.23.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.23.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.24.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.24.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.24.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.25.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.25.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.25.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.26.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.26.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.26.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.27.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.27.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.27.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.28.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.28.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.28.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.29.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.29.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.29.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.3.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.3.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.3.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.30.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.30.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.30.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.31.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.31.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.31.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.32.down_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.32.gate_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.32.up_proj.weight": "model-00002-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.4.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.4.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.4.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.5.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.5.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.5.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.6.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.6.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.6.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.7.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.7.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.7.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.8.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.8.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.8.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.9.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.9.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_to_speech_embedding_mlps.9.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "local_transformer.norm.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.0.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.1.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.10.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.11.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.12.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.13.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.14.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.15.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.16.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.17.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.18.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.19.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.2.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.20.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.21.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.22.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.23.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.24.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.25.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.26.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.27.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.28.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.29.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.3.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.30.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.31.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.32.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.4.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.5.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.6.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.7.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.8.weight": "model-00001-of-00002.safetensors", | |
| "model.embedding_list.9.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.language_model.norm.weight": "model-00001-of-00002.safetensors", | |
| "speech_embedding_to_local_mlp.down_proj.weight": "model-00001-of-00002.safetensors", | |
| "speech_embedding_to_local_mlp.gate_proj.weight": "model-00001-of-00002.safetensors", | |
| "speech_embedding_to_local_mlp.up_proj.weight": "model-00001-of-00002.safetensors" | |
| } | |
| } | |