orig script

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "./checkpoints/llava1.5_7b_with_alignment",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_projector_lr": 3e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67953d2a51bea4b508c4f196befe3eb1c9ccd6cf521a187bd17f332f18e4f8a1
+size 9976620122

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1895f5f0a7ce6eb378a2da33677636c6057c585c35d409e4f55dffaa1a9e09
+size 4149434554

pytorch_model.bin.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 14125805568
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,904 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2932,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 1.238,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.8443,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.0454545454545454e-05,
+      "loss": 0.7152,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.7272727272727273e-05,
+      "loss": 0.6588,
+      "step": 80
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9998682174346518e-05,
+      "loss": 0.6264,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.999062963389176e-05,
+      "loss": 0.6058,
+      "step": 120
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.9975260603791104e-05,
+      "loss": 0.5715,
+      "step": 140
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.995258258522044e-05,
+      "loss": 0.5611,
+      "step": 160
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.992260664666002e-05,
+      "loss": 0.5312,
+      "step": 180
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9885347418492256e-05,
+      "loss": 0.5117,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9840823085861047e-05,
+      "loss": 0.4949,
+      "step": 220
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.9789055379796153e-05,
+      "loss": 0.4821,
+      "step": 240
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9730069566606912e-05,
+      "loss": 0.4631,
+      "step": 260
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9663894435550477e-05,
+      "loss": 0.4513,
+      "step": 280
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.9590562284780622e-05,
+      "loss": 0.4311,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.951010890558398e-05,
+      "loss": 0.4225,
+      "step": 320
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9422573564911305e-05,
+      "loss": 0.4159,
+      "step": 340
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.9327998986212484e-05,
+      "loss": 0.4096,
+      "step": 360
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.9226431328584402e-05,
+      "loss": 0.3839,
+      "step": 380
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.911792016424208e-05,
+      "loss": 0.378,
+      "step": 400
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9002518454323883e-05,
+      "loss": 0.3646,
+      "step": 420
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.888028252304277e-05,
+      "loss": 0.361,
+      "step": 440
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.8751272030196054e-05,
+      "loss": 0.3491,
+      "step": 460
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.8615549942047203e-05,
+      "loss": 0.3421,
+      "step": 480
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.8473182500593847e-05,
+      "loss": 0.327,
+      "step": 500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.832423919123698e-05,
+      "loss": 0.3242,
+      "step": 520
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.816879270886717e-05,
+      "loss": 0.3259,
+      "step": 540
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.8006918922384294e-05,
+      "loss": 0.3132,
+      "step": 560
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.7838696837668128e-05,
+      "loss": 0.2993,
+      "step": 580
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.7664208559017903e-05,
+      "loss": 0.3023,
+      "step": 600
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.748353924907957e-05,
+      "loss": 0.2966,
+      "step": 620
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.7296777087280396e-05,
+      "loss": 0.2891,
+      "step": 640
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.7104013226791156e-05,
+      "loss": 0.2873,
+      "step": 660
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.690534175003692e-05,
+      "loss": 0.2815,
+      "step": 680
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6700859622778184e-05,
+      "loss": 0.2736,
+      "step": 700
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.649066664678467e-05,
+      "loss": 0.2677,
+      "step": 720
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6274865411125028e-05,
+      "loss": 0.2739,
+      "step": 740
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.605356124209607e-05,
+      "loss": 0.2671,
+      "step": 760
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.5826862151816088e-05,
+      "loss": 0.2509,
+      "step": 780
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.5594878785507284e-05,
+      "loss": 0.2629,
+      "step": 800
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.5357724367493052e-05,
+      "loss": 0.2487,
+      "step": 820
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.5115514645936506e-05,
+      "loss": 0.2493,
+      "step": 840
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.4868367836347142e-05,
+      "loss": 0.2477,
+      "step": 860
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.4616404563883302e-05,
+      "loss": 0.2453,
+      "step": 880
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.4359747804478576e-05,
+      "loss": 0.2372,
+      "step": 900
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.4098522824820782e-05,
+      "loss": 0.2421,
+      "step": 920
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.3832857121212992e-05,
+      "loss": 0.2456,
+      "step": 940
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.3562880357346273e-05,
+      "loss": 0.2398,
+      "step": 960
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.3288724301014613e-05,
+      "loss": 0.2247,
+      "step": 980
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.3010522759802922e-05,
+      "loss": 0.2349,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.2728411515779426e-05,
+      "loss": 0.2216,
+      "step": 1020
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.2442528259224412e-05,
+      "loss": 0.2281,
+      "step": 1040
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.2153012521427593e-05,
+      "loss": 0.2214,
+      "step": 1060
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.186000560658697e-05,
+      "loss": 0.2132,
+      "step": 1080
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.1563650522842357e-05,
+      "loss": 0.2161,
+      "step": 1100
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.1264091912477285e-05,
+      "loss": 0.2122,
+      "step": 1120
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.09614759813233e-05,
+      "loss": 0.2135,
+      "step": 1140
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.0655950427401163e-05,
+      "loss": 0.2028,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0347664368833765e-05,
+      "loss": 0.209,
+      "step": 1180
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.003676827106589e-05,
+      "loss": 0.1944,
+      "step": 1200
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.9723413873426427e-05,
+      "loss": 0.2033,
+      "step": 1220
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.9407754115068814e-05,
+      "loss": 0.1931,
+      "step": 1240
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.908994306032592e-05,
+      "loss": 0.2005,
+      "step": 1260
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.877013582351569e-05,
+      "loss": 0.1885,
+      "step": 1280
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.8448488493234402e-05,
+      "loss": 0.1958,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.812515805617435e-05,
+      "loss": 0.1954,
+      "step": 1320
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.780030232050322e-05,
+      "loss": 0.1871,
+      "step": 1340
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.7474079838842513e-05,
+      "loss": 0.192,
+      "step": 1360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7146649830882635e-05,
+      "loss": 0.2031,
+      "step": 1380
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.681817210567241e-05,
+      "loss": 0.1877,
+      "step": 1400
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6488806983620927e-05,
+      "loss": 0.1889,
+      "step": 1420
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.615871521824982e-05,
+      "loss": 0.172,
+      "step": 1440
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.582805791773416e-05,
+      "loss": 0.1813,
+      "step": 1460
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5496996466270265e-05,
+      "loss": 0.1478,
+      "step": 1480
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5165692445308728e-05,
+      "loss": 0.1298,
+      "step": 1500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.4834307554691274e-05,
+      "loss": 0.126,
+      "step": 1520
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.450300353372974e-05,
+      "loss": 0.1224,
+      "step": 1540
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.417194208226584e-05,
+      "loss": 0.1246,
+      "step": 1560
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.3841284781750184e-05,
+      "loss": 0.1192,
+      "step": 1580
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.3511193016379079e-05,
+      "loss": 0.1216,
+      "step": 1600
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.3181827894327595e-05,
+      "loss": 0.1227,
+      "step": 1620
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.2853350169117368e-05,
+      "loss": 0.1248,
+      "step": 1640
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.2525920161157491e-05,
+      "loss": 0.1153,
+      "step": 1660
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.2199697679496782e-05,
+      "loss": 0.123,
+      "step": 1680
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.187484194382565e-05,
+      "loss": 0.1215,
+      "step": 1700
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.1551511506765599e-05,
+      "loss": 0.1206,
+      "step": 1720
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.1229864176484311e-05,
+      "loss": 0.1178,
+      "step": 1740
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.0910056939674083e-05,
+      "loss": 0.1163,
+      "step": 1760
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0592245884931188e-05,
+      "loss": 0.1214,
+      "step": 1780
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.0276586126573578e-05,
+      "loss": 0.1168,
+      "step": 1800
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 9.963231728934113e-06,
+      "loss": 0.1172,
+      "step": 1820
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 9.652335631166236e-06,
+      "loss": 0.1203,
+      "step": 1840
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 9.34404957259884e-06,
+      "loss": 0.1101,
+      "step": 1860
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.038524018676704e-06,
+      "loss": 0.1202,
+      "step": 1880
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 8.735908087522721e-06,
+      "loss": 0.1107,
+      "step": 1900
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 8.43634947715764e-06,
+      "loss": 0.1131,
+      "step": 1920
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 8.139994393413035e-06,
+      "loss": 0.1127,
+      "step": 1940
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 7.846987478572411e-06,
+      "loss": 0.1132,
+      "step": 1960
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 7.557471740775593e-06,
+      "loss": 0.1096,
+      "step": 1980
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 7.271588484220576e-06,
+      "loss": 0.1136,
+      "step": 2000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 6.989477240197081e-06,
+      "loss": 0.107,
+      "step": 2020
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 6.711275698985388e-06,
+      "loss": 0.1164,
+      "step": 2040
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 6.4371196426537295e-06,
+      "loss": 0.1066,
+      "step": 2060
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 6.167142878787007e-06,
+      "loss": 0.1075,
+      "step": 2080
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.901477175179223e-06,
+      "loss": 0.1045,
+      "step": 2100
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.640252195521428e-06,
+      "loss": 0.1092,
+      "step": 2120
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.383595436116703e-06,
+      "loss": 0.1129,
+      "step": 2140
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.13163216365286e-06,
+      "loss": 0.1035,
+      "step": 2160
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 4.8844853540634966e-06,
+      "loss": 0.1058,
+      "step": 2180
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.642275632506942e-06,
+      "loss": 0.105,
+      "step": 2200
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 4.4051212144927195e-06,
+      "loss": 0.0991,
+      "step": 2220
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.173137848183911e-06,
+      "loss": 0.1004,
+      "step": 2240
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 3.946438757903934e-06,
+      "loss": 0.1045,
+      "step": 2260
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.7251345888749743e-06,
+      "loss": 0.1071,
+      "step": 2280
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 3.5093333532153316e-06,
+      "loss": 0.0949,
+      "step": 2300
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.29914037722182e-06,
+      "loss": 0.1034,
+      "step": 2320
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.094658249963081e-06,
+      "loss": 0.0951,
+      "step": 2340
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.8959867732088483e-06,
+      "loss": 0.0991,
+      "step": 2360
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.7032229127196052e-06,
+      "loss": 0.1019,
+      "step": 2380
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.5164607509204297e-06,
+      "loss": 0.0976,
+      "step": 2400
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.335791440982097e-06,
+      "loss": 0.1019,
+      "step": 2420
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.1613031623318736e-06,
+      "loss": 0.0971,
+      "step": 2440
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.9930810776157132e-06,
+      "loss": 0.0974,
+      "step": 2460
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.831207291132832e-06,
+      "loss": 0.0919,
+      "step": 2480
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.6757608087630249e-06,
+      "loss": 0.0943,
+      "step": 2500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.5268174994061546e-06,
+      "loss": 0.0944,
+      "step": 2520
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.3844500579527997e-06,
+      "loss": 0.1012,
+      "step": 2540
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.248727969803945e-06,
+      "loss": 0.0983,
+      "step": 2560
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.1197174769572293e-06,
+      "loss": 0.0958,
+      "step": 2580
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 9.974815456761176e-07,
+      "loss": 0.1012,
+      "step": 2600
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 8.82079835757924e-07,
+      "loss": 0.0955,
+      "step": 2620
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.735686714155987e-07,
+      "loss": 0.0936,
+      "step": 2640
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 6.720010137875182e-07,
+      "loss": 0.1008,
+      "step": 2660
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 5.774264350886937e-07,
+      "loss": 0.0977,
+      "step": 2680
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 4.898910944160235e-07,
+      "loss": 0.0968,
+      "step": 2700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 4.094377152193784e-07,
+      "loss": 0.0927,
+      "step": 2720
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.3610556444952643e-07,
+      "loss": 0.0916,
+      "step": 2740
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.699304333930902e-07,
+      "loss": 0.092,
+      "step": 2760
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.1094462020384953e-07,
+      "loss": 0.1012,
+      "step": 2780
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.5917691413895597e-07,
+      "loss": 0.099,
+      "step": 2800
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.1465258150774927e-07,
+      "loss": 0.0947,
+      "step": 2820
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.739335333998176e-08,
+      "loss": 0.0945,
+      "step": 2840
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.741741477956252e-08,
+      "loss": 0.0896,
+      "step": 2860
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.4739396208898757e-08,
+      "loss": 0.0956,
+      "step": 2880
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 9.370366108241157e-09,
+      "loss": 0.0955,
+      "step": 2900
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.3178256534834843e-09,
+      "loss": 0.0931,
+      "step": 2920
+    },
+    {
+      "epoch": 2.0,
+      "step": 2932,
+      "total_flos": 341864985133056.0,
+      "train_loss": 0.2192974041786558,
+      "train_runtime": 28403.1411,
+      "train_samples_per_second": 8.253,
+      "train_steps_per_second": 0.103
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2932,
+  "num_train_epochs": 2,
+  "save_steps": 50000,
+  "total_flos": 341864985133056.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e73d9842731ba94e75fd54b57a7834c9e314ddf4e7b38d32cfb7ffa745b8b9
+size 6075