| { | |
| "metadata": { | |
| "total_size": 19908958240 | |
| }, | |
| "weight_map": { | |
| "language_model.model.layers.0.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.0.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.1.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.10.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.attn_gate": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.cross_attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.ff_gate": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.ffn_2.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.ffn_2.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.ffn_2.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.11.gated_cross_attn_layer.ffn_norm_2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.12.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.13.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.14.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.15.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.attn_gate": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.cross_attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.ff_gate": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.ffn_2.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.ffn_2.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.ffn_2.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.15.gated_cross_attn_layer.ffn_norm_2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.16.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.17.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.18.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.attn_gate": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.cross_attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.ff_gate": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.ffn_2.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.ffn_2.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.ffn_2.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.19.gated_cross_attn_layer.ffn_norm_2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.2.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.20.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.21.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.22.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.feed_forward.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.feed_forward.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.decoder_layer.ffn_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.attn_gate": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.cross_attention_norm.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.ff_gate": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.ffn_2.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.ffn_2.w2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.ffn_2.w3.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.23.gated_cross_attn_layer.ffn_norm_2.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.attention.wo.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.attention.wqkv.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.feed_forward.w1.weight": "model-00003-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.24.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.25.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.26.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.attn_gate": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.cross_attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.ff_gate": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.ffn_2.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.ffn_2.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.ffn_2.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.27.gated_cross_attn_layer.ffn_norm_2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.28.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.29.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.attn_gate": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.cross_attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.ff_gate": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.ffn_2.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.ffn_2.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.ffn_2.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.3.gated_cross_attn_layer.ffn_norm_2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.30.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.attention.wo.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.attention.wqkv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.feed_forward.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.feed_forward.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.feed_forward.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.decoder_layer.ffn_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.attn_gate": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.cross_attention_norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.ff_gate": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.ffn_2.w1.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.ffn_2.w2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.ffn_2.w3.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.31.gated_cross_attn_layer.ffn_norm_2.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.4.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.5.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.attention.wo.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.attention.wqkv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.feed_forward.w1.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.feed_forward.w2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.feed_forward.w3.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.6.decoder_layer.ffn_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.attn_gate": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.cross_attention_norm.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.cross_attn.to_kv.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.cross_attn.to_out.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.cross_attn.to_q.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.ff_gate": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.ffn_2.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.ffn_2.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.ffn_2.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.7.gated_cross_attn_layer.ffn_norm_2.weight": "model-00001-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.8.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.attention.wo.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.attention.wqkv.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.attention_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.feed_forward.w1.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.feed_forward.w2.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.feed_forward.w3.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.layers.9.decoder_layer.ffn_norm.weight": "model-00002-of-00005.safetensors", | |
| "language_model.model.norm.weight": "model-00004-of-00005.safetensors", | |
| "language_model.model.tok_embeddings.weight": "model-00001-of-00005.safetensors", | |
| "language_model.output.weight": "model-00004-of-00005.safetensors", | |
| "mlp1.0.bias": "model-00004-of-00005.safetensors", | |
| "mlp1.0.weight": "model-00004-of-00005.safetensors", | |
| "mlp1.1.bias": "model-00005-of-00005.safetensors", | |
| "mlp1.1.weight": "model-00005-of-00005.safetensors", | |
| "mlp1.3.bias": "model-00005-of-00005.safetensors", | |
| "mlp1.3.weight": "model-00005-of-00005.safetensors", | |
| "vision_model.embeddings.class_embedding": "model-00001-of-00005.safetensors", | |
| "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.embeddings.position_embedding": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.ls1": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.ls2": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00005.safetensors", | |
| "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00005.safetensors" | |
| } | |
| } | |