diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json" new file mode 100644--- /dev/null +++ "b/model.safetensors.index.json" @@ -0,0 +1,1338 @@ +{ + "metadata": { + "total_size": 23022008646 + }, + "weight_map": { + "embed_tokens.audio_model.encoder.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.0.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.1.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.10.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.11.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.12.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.13.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.14.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.15.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.16.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.17.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.18.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.19.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.2.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.20.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.21.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.22.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.23.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.3.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.4.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.5.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.6.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.7.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.8.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.k_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.k_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.out_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.out_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.q_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.q_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.v_proj.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.attention.v_proj.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.feed_forward.intermediate_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.feed_forward.intermediate_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.feed_forward.output_dense.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.feed_forward.output_dense.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.final_layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.final_layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.layers.9.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.pos_conv_embed.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.pos_conv_embed.conv.parametrizations.weight.original0": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.encoder.pos_conv_embed.conv.parametrizations.weight.original1": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.0.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.0.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.0.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.0.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.1.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.1.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.1.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.1.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.2.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.2.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.2.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.2.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.3.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.3.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.3.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.3.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.4.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.4.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.4.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.4.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.5.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.5.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.5.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.5.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.6.conv.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.6.conv.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.6.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_extractor.conv_layers.6.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_projection.layer_norm.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_projection.layer_norm.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_projection.projection.bias": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.feature_projection.projection.weight": "model-00005-of-00005.safetensors", + "embed_tokens.audio_model.masked_spec_embed": "model-00005-of-00005.safetensors", + "embed_tokens.end_of_audio": "model-00005-of-00005.safetensors", + "embed_tokens.start_of_audio": "model-00005-of-00005.safetensors", + "embed_tokens.text_embeddings.weight": "model-00005-of-00005.safetensors", + "language_model.lm_head.weight": "model-00005-of-00005.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn_attn_gate": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.cross_attn_mlp_gate": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn_attn_gate": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.cross_attn_mlp_gate": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn_attn_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.cross_attn_mlp_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn_attn_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.cross_attn_mlp_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn_attn_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.cross_attn_mlp_gate": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn_attn_gate": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.cross_attn_mlp_gate": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.norm.weight": "model-00005-of-00005.safetensors", + "multi_modal_projector.bias": "model-00005-of-00005.safetensors", + "multi_modal_projector.weight": "model-00005-of-00005.safetensors", + "vision_model.class_embedding": "model-00001-of-00005.safetensors", + "vision_model.gated_positional_embedding.embedding": "model-00001-of-00005.safetensors", + "vision_model.gated_positional_embedding.gate": "model-00001-of-00005.safetensors", + "vision_model.gated_positional_embedding.tile_embedding.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors", + "vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors", + "vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors", + "vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors", + "vision_model.patch_embedding.weight": "model-00001-of-00005.safetensors", + "vision_model.post_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors", + "vision_model.post_tile_positional_embedding.gate": "model-00001-of-00005.safetensors", + "vision_model.pre_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors", + "vision_model.pre_tile_positional_embedding.gate": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors" + } +}