model

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,200 @@
+{
+  "_name_or_path": "/root/nfs/LLM4CodeBeta/FLAME_MD/models/lmms-lab/llava-onevision-qwen2-7b-ov",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "ignore_index": -100,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mm_hidden_size": 1152,
+  "mm_newline_position": "one_token",
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "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": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-06,
+  "model_type": "llava",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 16384,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064,
+  "vision_tower_pretrained": null
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9593e0582caa94bacd5842b2f1191187c6cfe7d5ba0ce28197438a8b2e44c566
+size 4877668032

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931ad310dcac3afaaecda5f8a1381eca560b6a18809e7917d38d1a07302e446f
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67ca85339eef3dbd6f13acff94f69c6b723cdd66e25d9884aebb3dc93891645
+size 4994571904

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00a74d809b53b0362a53291963f0e1258f6df8126b9f2990539ccc4e3dbd42c
+size 1255812224

model.safetensors.index.json

@@ -0,0 +1,772 @@
+{
+  "metadata": {
+    "total_size": 16060697664
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.image_newline": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.mm_projector.0.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.0.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector.2.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1626 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9958965941731637,
+  "eval_steps": 500,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.9784271717071533,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.3187,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.0431859493255615,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.3228,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.811855435371399,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.3149,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.6479771137237549,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.2716,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4887213706970215,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.2539,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.94520103931427,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.2564,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.406177043914795,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2402,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.7317909598350525,
+      "learning_rate": 2.4998737044926244e-05,
+      "loss": 0.219,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7414913773536682,
+      "learning_rate": 2.4994948434913852e-05,
+      "loss": 0.208,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.626851499080658,
+      "learning_rate": 2.498863493553791e-05,
+      "loss": 0.1984,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.5056077837944031,
+      "learning_rate": 2.4979797822584984e-05,
+      "loss": 0.1923,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.5833318829536438,
+      "learning_rate": 2.4968438881795332e-05,
+      "loss": 0.1887,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.4281924366950989,
+      "learning_rate": 2.4954560408502066e-05,
+      "loss": 0.1807,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.43832024931907654,
+      "learning_rate": 2.4938165207167307e-05,
+      "loss": 0.1732,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.46066734194755554,
+      "learning_rate": 2.4919256590815486e-05,
+      "loss": 0.1758,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3688454031944275,
+      "learning_rate": 2.489783838036388e-05,
+      "loss": 0.1713,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.489734023809433,
+      "learning_rate": 2.48739149038505e-05,
+      "loss": 0.1655,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.33106324076652527,
+      "learning_rate": 2.4847490995559502e-05,
+      "loss": 0.1585,
+      "step": 18
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3802390694618225,
+      "learning_rate": 2.4818571995044346e-05,
+      "loss": 0.1584,
+      "step": 19
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.33007049560546875,
+      "learning_rate": 2.4787163746048776e-05,
+      "loss": 0.1555,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.27524107694625854,
+      "learning_rate": 2.4753272595325976e-05,
+      "loss": 0.1551,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3649667501449585,
+      "learning_rate": 2.471690539135607e-05,
+      "loss": 0.1537,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.21732817590236664,
+      "learning_rate": 2.467806948296223e-05,
+      "loss": 0.154,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2916033864021301,
+      "learning_rate": 2.463677271782565e-05,
+      "loss": 0.1499,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.24713736772537231,
+      "learning_rate": 2.459302344089979e-05,
+      "loss": 0.1508,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.45957571268081665,
+      "learning_rate": 2.4546830492724048e-05,
+      "loss": 0.1481,
+      "step": 26
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2814270257949829,
+      "learning_rate": 2.449820320763735e-05,
+      "loss": 0.1448,
+      "step": 27
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.18213127553462982,
+      "learning_rate": 2.4447151411891924e-05,
+      "loss": 0.1433,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2358454018831253,
+      "learning_rate": 2.4393685421667677e-05,
+      "loss": 0.1421,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.19716422259807587,
+      "learning_rate": 2.43378160409876e-05,
+      "loss": 0.1395,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.190892294049263,
+      "learning_rate": 2.427955455953453e-05,
+      "loss": 0.1386,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1897621750831604,
+      "learning_rate": 2.4218912750369848e-05,
+      "loss": 0.1374,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.19067858159542084,
+      "learning_rate": 2.4155902867554447e-05,
+      "loss": 0.1388,
+      "step": 33
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2128712385892868,
+      "learning_rate": 2.409053764367252e-05,
+      "loss": 0.1369,
+      "step": 34
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1807384490966797,
+      "learning_rate": 2.4022830287258646e-05,
+      "loss": 0.1346,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1716810017824173,
+      "learning_rate": 2.3952794480128716e-05,
+      "loss": 0.1305,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1860591322183609,
+      "learning_rate": 2.3880444374615208e-05,
+      "loss": 0.1335,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.16601909697055817,
+      "learning_rate": 2.380579459070737e-05,
+      "loss": 0.131,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.20423191785812378,
+      "learning_rate": 2.372886021309694e-05,
+      "loss": 0.1295,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.20887944102287292,
+      "learning_rate": 2.3649656788129932e-05,
+      "loss": 0.1275,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.16653062403202057,
+      "learning_rate": 2.3568200320665124e-05,
+      "loss": 0.1258,
+      "step": 41
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.25706666707992554,
+      "learning_rate": 2.348450727083994e-05,
+      "loss": 0.1292,
+      "step": 42
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.22015853226184845,
+      "learning_rate": 2.3398594550744292e-05,
+      "loss": 0.1283,
+      "step": 43
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.166912242770195,
+      "learning_rate": 2.3310479521003087e-05,
+      "loss": 0.1256,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.25648847222328186,
+      "learning_rate": 2.3220179987268153e-05,
+      "loss": 0.1243,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.25875574350357056,
+      "learning_rate": 2.312771419662018e-05,
+      "loss": 0.1235,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1738785058259964,
+      "learning_rate": 2.303310083388147e-05,
+      "loss": 0.1236,
+      "step": 47
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.5825874209403992,
+      "learning_rate": 2.293635901784028e-05,
+      "loss": 0.1253,
+      "step": 48
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2370326668024063,
+      "learning_rate": 2.2837508297387384e-05,
+      "loss": 0.1202,
+      "step": 49
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.23894409835338593,
+      "learning_rate": 2.2736568647565813e-05,
+      "loss": 0.1241,
+      "step": 50
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2987692654132843,
+      "learning_rate": 2.2633560465534438e-05,
+      "loss": 0.121,
+      "step": 51
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.15940450131893158,
+      "learning_rate": 2.252850456644623e-05,
+      "loss": 0.1214,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.23472265899181366,
+      "learning_rate": 2.2421422179242118e-05,
+      "loss": 0.1233,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1976010501384735,
+      "learning_rate": 2.2312334942361186e-05,
+      "loss": 0.1217,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1780591905117035,
+      "learning_rate": 2.220126489936811e-05,
+      "loss": 0.1217,
+      "step": 55
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.1945282518863678,
+      "learning_rate": 2.2088234494498793e-05,
+      "loss": 0.1193,
+      "step": 56
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.15890829265117645,
+      "learning_rate": 2.1973266568124963e-05,
+      "loss": 0.1195,
+      "step": 57
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.18175674974918365,
+      "learning_rate": 2.1856384352138765e-05,
+      "loss": 0.1186,
+      "step": 58
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.18463999032974243,
+      "learning_rate": 2.173761146525824e-05,
+      "loss": 0.1173,
+      "step": 59
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.16729244589805603,
+      "learning_rate": 2.1616971908254602e-05,
+      "loss": 0.1163,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2122853696346283,
+      "learning_rate": 2.1494490059102352e-05,
+      "loss": 0.1189,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.17801564931869507,
+      "learning_rate": 2.137019066805314e-05,
+      "loss": 0.115,
+      "step": 62
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.15604089200496674,
+      "learning_rate": 2.1244098852634424e-05,
+      "loss": 0.1156,
+      "step": 63
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.18216270208358765,
+      "learning_rate": 2.1116240092573887e-05,
+      "loss": 0.1162,
+      "step": 64
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1924414336681366,
+      "learning_rate": 2.0986640224650684e-05,
+      "loss": 0.1157,
+      "step": 65
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1668936014175415,
+      "learning_rate": 2.0855325437474545e-05,
+      "loss": 0.1163,
+      "step": 66
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.23567163944244385,
+      "learning_rate": 2.072232226619374e-05,
+      "loss": 0.1165,
+      "step": 67
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2859678268432617,
+      "learning_rate": 2.058765758713307e-05,
+      "loss": 0.1134,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.17498141527175903,
+      "learning_rate": 2.0451358612362883e-05,
+      "loss": 0.1145,
+      "step": 69
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.21807977557182312,
+      "learning_rate": 2.0313452884200258e-05,
+      "loss": 0.115,
+      "step": 70
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.18138931691646576,
+      "learning_rate": 2.0173968269643438e-05,
+      "loss": 0.1118,
+      "step": 71
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2159774750471115,
+      "learning_rate": 2.0032932954740708e-05,
+      "loss": 0.1119,
+      "step": 72
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.170742467045784,
+      "learning_rate": 1.98903754388947e-05,
+      "loss": 0.1094,
+      "step": 73
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.22051601111888885,
+      "learning_rate": 1.9746324529103484e-05,
+      "loss": 0.1131,
+      "step": 74
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.17040607333183289,
+      "learning_rate": 1.9600809334139446e-05,
+      "loss": 0.1108,
+      "step": 75
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.1619778275489807,
+      "learning_rate": 1.94538592586672e-05,
+      "loss": 0.1105,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.1628006547689438,
+      "learning_rate": 1.9305503997301683e-05,
+      "loss": 0.1113,
+      "step": 77
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14687460660934448,
+      "learning_rate": 1.9155773528607706e-05,
+      "loss": 0.1094,
+      "step": 78
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.1578996777534485,
+      "learning_rate": 1.9004698109042098e-05,
+      "loss": 0.112,
+      "step": 79
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.14307241141796112,
+      "learning_rate": 1.885230826683967e-05,
+      "loss": 0.1089,
+      "step": 80
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1476210057735443,
+      "learning_rate": 1.8698634795844334e-05,
+      "loss": 0.1098,
+      "step": 81
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.14934228360652924,
+      "learning_rate": 1.8543708749286472e-05,
+      "loss": 0.1127,
+      "step": 82
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.15839678049087524,
+      "learning_rate": 1.8387561433507935e-05,
+      "loss": 0.1099,
+      "step": 83
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.13993161916732788,
+      "learning_rate": 1.8230224401635877e-05,
+      "loss": 0.1091,
+      "step": 84
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.18795226514339447,
+      "learning_rate": 1.8071729447206733e-05,
+      "loss": 0.1082,
+      "step": 85
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15649783611297607,
+      "learning_rate": 1.791210859774159e-05,
+      "loss": 0.1078,
+      "step": 86
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1590489000082016,
+      "learning_rate": 1.775139410827433e-05,
+      "loss": 0.1089,
+      "step": 87
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.16150489449501038,
+      "learning_rate": 1.7589618454833732e-05,
+      "loss": 0.1108,
+      "step": 88
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.18347468972206116,
+      "learning_rate": 1.742681432788097e-05,
+      "loss": 0.1099,
+      "step": 89
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.19950658082962036,
+      "learning_rate": 1.7263014625703755e-05,
+      "loss": 0.1098,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.16751055419445038,
+      "learning_rate": 1.7098252447768474e-05,
+      "loss": 0.1065,
+      "step": 91
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1769932210445404,
+      "learning_rate": 1.6932561088031695e-05,
+      "loss": 0.1074,
+      "step": 92
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1737072914838791,
+      "learning_rate": 1.6765974028212384e-05,
+      "loss": 0.1071,
+      "step": 93
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.15936574339866638,
+      "learning_rate": 1.6598524931026116e-05,
+      "loss": 0.1055,
+      "step": 94
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.15544667840003967,
+      "learning_rate": 1.64302476333828e-05,
+      "loss": 0.1058,
+      "step": 95
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.13811974227428436,
+      "learning_rate": 1.626117613954913e-05,
+      "loss": 0.1047,
+      "step": 96
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.1541808396577835,
+      "learning_rate": 1.6091344614277258e-05,
+      "loss": 0.1072,
+      "step": 97
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.15534372627735138,
+      "learning_rate": 1.5920787375901038e-05,
+      "loss": 0.1052,
+      "step": 98
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.1353050172328949,
+      "learning_rate": 1.5749538889401193e-05,
+      "loss": 0.1042,
+      "step": 99
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.22836215794086456,
+      "learning_rate": 1.5577633759440906e-05,
+      "loss": 0.1039,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.17876186966896057,
+      "learning_rate": 1.540510672337316e-05,
+      "loss": 0.1043,
+      "step": 101
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.15621179342269897,
+      "learning_rate": 1.5231992644221237e-05,
+      "loss": 0.1044,
+      "step": 102
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.14718405902385712,
+      "learning_rate": 1.5058326503633877e-05,
+      "loss": 0.105,
+      "step": 103
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.21009863913059235,
+      "learning_rate": 1.4884143394816422e-05,
+      "loss": 0.1033,
+      "step": 104
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.16238641738891602,
+      "learning_rate": 1.4709478515439437e-05,
+      "loss": 0.1057,
+      "step": 105
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.18099305033683777,
+      "learning_rate": 1.4534367160526222e-05,
+      "loss": 0.103,
+      "step": 106
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1507808268070221,
+      "learning_rate": 1.4358844715320646e-05,
+      "loss": 0.1033,
+      "step": 107
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.18585935235023499,
+      "learning_rate": 1.4182946648136743e-05,
+      "loss": 0.1034,
+      "step": 108
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.14103898406028748,
+      "learning_rate": 1.4006708503191538e-05,
+      "loss": 0.1043,
+      "step": 109
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.17270641028881073,
+      "learning_rate": 1.383016589342253e-05,
+      "loss": 0.1024,
+      "step": 110
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.14897307753562927,
+      "learning_rate": 1.3653354493291276e-05,
+      "loss": 0.1016,
+      "step": 111
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1660037636756897,
+      "learning_rate": 1.347631003157456e-05,
+      "loss": 0.104,
+      "step": 112
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.13886870443820953,
+      "learning_rate": 1.3299068284144572e-05,
+      "loss": 0.1038,
+      "step": 113
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1572652906179428,
+      "learning_rate": 1.3121665066739585e-05,
+      "loss": 0.1025,
+      "step": 114
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.14484383165836334,
+      "learning_rate": 1.2944136227726567e-05,
+      "loss": 0.0976,
+      "step": 115
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.14088276028633118,
+      "learning_rate": 1.2766517640857185e-05,
+      "loss": 0.0968,
+      "step": 116
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.15066668391227722,
+      "learning_rate": 1.258884519801872e-05,
+      "loss": 0.0945,
+      "step": 117
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.13847996294498444,
+      "learning_rate": 1.241115480198128e-05,
+      "loss": 0.0935,
+      "step": 118
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.16715236008167267,
+      "learning_rate": 1.2233482359142818e-05,
+      "loss": 0.0931,
+      "step": 119
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.1418904960155487,
+      "learning_rate": 1.205586377227344e-05,
+      "loss": 0.092,
+      "step": 120
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.14103123545646667,
+      "learning_rate": 1.1878334933260416e-05,
+      "loss": 0.0927,
+      "step": 121
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.1596936285495758,
+      "learning_rate": 1.1700931715855431e-05,
+      "loss": 0.093,
+      "step": 122
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.14014697074890137,
+      "learning_rate": 1.1523689968425443e-05,
+      "loss": 0.0924,
+      "step": 123
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.133283793926239,
+      "learning_rate": 1.1346645506708726e-05,
+      "loss": 0.0917,
+      "step": 124
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.16669759154319763,
+      "learning_rate": 1.1169834106577472e-05,
+      "loss": 0.0942,
+      "step": 125
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.12519578635692596,
+      "learning_rate": 1.0993291496808463e-05,
+      "loss": 0.0909,
+      "step": 126
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.15250040590763092,
+      "learning_rate": 1.081705335186326e-05,
+      "loss": 0.0947,
+      "step": 127
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.12160287797451019,
+      "learning_rate": 1.0641155284679352e-05,
+      "loss": 0.0933,
+      "step": 128
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.15549159049987793,
+      "learning_rate": 1.0465632839473777e-05,
+      "loss": 0.0938,
+      "step": 129
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.12834098935127258,
+      "learning_rate": 1.0290521484560568e-05,
+      "loss": 0.0937,
+      "step": 130
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.13635213673114777,
+      "learning_rate": 1.0115856605183581e-05,
+      "loss": 0.0936,
+      "step": 131
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.1392364799976349,
+      "learning_rate": 9.941673496366128e-06,
+      "loss": 0.0923,
+      "step": 132
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.12665756046772003,
+      "learning_rate": 9.768007355778764e-06,
+      "loss": 0.0932,
+      "step": 133
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.13647811114788055,
+      "learning_rate": 9.594893276626845e-06,
+      "loss": 0.0922,
+      "step": 134
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.12814579904079437,
+      "learning_rate": 9.422366240559092e-06,
+      "loss": 0.0906,
+      "step": 135
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.1345747858285904,
+      "learning_rate": 9.25046111059881e-06,
+      "loss": 0.0913,
+      "step": 136
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.13295944035053253,
+      "learning_rate": 9.079212624098965e-06,
+      "loss": 0.0905,
+      "step": 137
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.12242992967367172,
+      "learning_rate": 8.908655385722745e-06,
+      "loss": 0.0904,
+      "step": 138
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.12390441447496414,
+      "learning_rate": 8.738823860450874e-06,
+      "loss": 0.0906,
+      "step": 139
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.149146169424057,
+      "learning_rate": 8.569752366617206e-06,
+      "loss": 0.0909,
+      "step": 140
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.12326322495937347,
+      "learning_rate": 8.40147506897389e-06,
+      "loss": 0.09,
+      "step": 141
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.11873169988393784,
+      "learning_rate": 8.23402597178762e-06,
+      "loss": 0.0928,
+      "step": 142
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.1468285620212555,
+      "learning_rate": 8.067438911968305e-06,
+      "loss": 0.092,
+      "step": 143
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.144583061337471,
+      "learning_rate": 7.90174755223153e-06,
+      "loss": 0.0907,
+      "step": 144
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.1313328891992569,
+      "learning_rate": 7.736985374296246e-06,
+      "loss": 0.0908,
+      "step": 145
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.125693678855896,
+      "learning_rate": 7.5731856721190305e-06,
+      "loss": 0.092,
+      "step": 146
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.13779418170452118,
+      "learning_rate": 7.41038154516627e-06,
+      "loss": 0.0892,
+      "step": 147
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.12493801862001419,
+      "learning_rate": 7.248605891725677e-06,
+      "loss": 0.0906,
+      "step": 148
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1351041942834854,
+      "learning_rate": 7.087891402258412e-06,
+      "loss": 0.0916,
+      "step": 149
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.12240799516439438,
+      "learning_rate": 6.928270552793273e-06,
+      "loss": 0.0906,
+      "step": 150
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.12128028273582458,
+      "learning_rate": 6.769775598364126e-06,
+      "loss": 0.0902,
+      "step": 151
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.12048149108886719,
+      "learning_rate": 6.612438566492066e-06,
+      "loss": 0.0902,
+      "step": 152
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.13495120406150818,
+      "learning_rate": 6.456291250713531e-06,
+      "loss": 0.092,
+      "step": 153
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.12498465925455093,
+      "learning_rate": 6.301365204155671e-06,
+      "loss": 0.0904,
+      "step": 154
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.1330261528491974,
+      "learning_rate": 6.147691733160338e-06,
+      "loss": 0.0892,
+      "step": 155
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.1269964575767517,
+      "learning_rate": 5.995301890957908e-06,
+      "loss": 0.0911,
+      "step": 156
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.12269794195890427,
+      "learning_rate": 5.8442264713922956e-06,
+      "loss": 0.0874,
+      "step": 157
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.12424512952566147,
+      "learning_rate": 5.694496002698316e-06,
+      "loss": 0.0908,
+      "step": 158
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.12635047733783722,
+      "learning_rate": 5.5461407413328005e-06,
+      "loss": 0.09,
+      "step": 159
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.12998418509960175,
+      "learning_rate": 5.399190665860554e-06,
+      "loss": 0.089,
+      "step": 160
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.12576289474964142,
+      "learning_rate": 5.253675470896521e-06,
+      "loss": 0.0897,
+      "step": 161
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.1248011440038681,
+      "learning_rate": 5.10962456110531e-06,
+      "loss": 0.0912,
+      "step": 162
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.12415432184934616,
+      "learning_rate": 4.967067045259296e-06,
+      "loss": 0.0886,
+      "step": 163
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.12433481216430664,
+      "learning_rate": 4.826031730356559e-06,
+      "loss": 0.089,
+      "step": 164
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.12309481203556061,
+      "learning_rate": 4.6865471157997455e-06,
+      "loss": 0.089,
+      "step": 165
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.11778941005468369,
+      "learning_rate": 4.548641387637119e-06,
+      "loss": 0.0884,
+      "step": 166
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.12076708674430847,
+      "learning_rate": 4.4123424128669325e-06,
+      "loss": 0.0901,
+      "step": 167
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.11921561509370804,
+      "learning_rate": 4.277677733806264e-06,
+      "loss": 0.0892,
+      "step": 168
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.11592774838209152,
+      "learning_rate": 4.144674562525456e-06,
+      "loss": 0.0874,
+      "step": 169
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.11221626400947571,
+      "learning_rate": 4.013359775349314e-06,
+      "loss": 0.0864,
+      "step": 170
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.11207148432731628,
+      "learning_rate": 3.883759907426117e-06,
+      "loss": 0.0881,
+      "step": 171
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.11837953329086304,
+      "learning_rate": 3.75590114736558e-06,
+      "loss": 0.0876,
+      "step": 172
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.11854910105466843,
+      "learning_rate": 3.629809331946862e-06,
+      "loss": 0.0893,
+      "step": 173
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.13525307178497314,
+      "learning_rate": 3.5055099408976485e-06,
+      "loss": 0.0878,
+      "step": 174
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.11121269315481186,
+      "learning_rate": 3.3830280917453996e-06,
+      "loss": 0.0901,
+      "step": 175
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.11432763934135437,
+      "learning_rate": 3.262388534741763e-06,
+      "loss": 0.0878,
+      "step": 176
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.11163436621427536,
+      "learning_rate": 3.143615647861235e-06,
+      "loss": 0.088,
+      "step": 177
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.13343572616577148,
+      "learning_rate": 3.0267334318750422e-06,
+      "loss": 0.0884,
+      "step": 178
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.12350989878177643,
+      "learning_rate": 2.9117655055012113e-06,
+      "loss": 0.0879,
+      "step": 179
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.10837291181087494,
+      "learning_rate": 2.798735100631891e-06,
+      "loss": 0.088,
+      "step": 180
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.10655102878808975,
+      "learning_rate": 2.6876650576388177e-06,
+      "loss": 0.0885,
+      "step": 181
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.11220265179872513,
+      "learning_rate": 2.5785778207578825e-06,
+      "loss": 0.0885,
+      "step": 182
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.11219317466020584,
+      "learning_rate": 2.4714954335537734e-06,
+      "loss": 0.0888,
+      "step": 183
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.12335841357707977,
+      "learning_rate": 2.3664395344655657e-06,
+      "loss": 0.0877,
+      "step": 184
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.109321229159832,
+      "learning_rate": 2.263431352434188e-06,
+      "loss": 0.0857,
+      "step": 185
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.10845804214477539,
+      "learning_rate": 2.162491702612618e-06,
+      "loss": 0.0875,
+      "step": 186
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.11222843080759048,
+      "learning_rate": 2.063640982159723e-06,
+      "loss": 0.0874,
+      "step": 187
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.11406616121530533,
+      "learning_rate": 1.96689916611853e-06,
+      "loss": 0.088,
+      "step": 188
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.11157534271478653,
+      "learning_rate": 1.8722858033798252e-06,
+      "loss": 0.0882,
+      "step": 189
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.10842332988977432,
+      "learning_rate": 1.7798200127318518e-06,
+      "loss": 0.0866,
+      "step": 190
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.10400620102882385,
+      "learning_rate": 1.6895204789969172e-06,
+      "loss": 0.0863,
+      "step": 191
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.1095794215798378,
+      "learning_rate": 1.601405449255712e-06,
+      "loss": 0.0879,
+      "step": 192
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.10124927014112473,
+      "learning_rate": 1.515492729160059e-06,
+      "loss": 0.0861,
+      "step": 193
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.1050131767988205,
+      "learning_rate": 1.4317996793348776e-06,
+      "loss": 0.0869,
+      "step": 194
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.1175614446401596,
+      "learning_rate": 1.3503432118700711e-06,
+      "loss": 0.0876,
+      "step": 195
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.12262062728404999,
+      "learning_rate": 1.2711397869030611e-06,
+      "loss": 0.0884,
+      "step": 196
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.10788723081350327,
+      "learning_rate": 1.1942054092926314e-06,
+      "loss": 0.0865,
+      "step": 197
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.10877244174480438,
+      "learning_rate": 1.1195556253847938e-06,
+      "loss": 0.0869,
+      "step": 198
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.1057361289858818,
+      "learning_rate": 1.0472055198712847e-06,
+      "loss": 0.0871,
+      "step": 199
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.11003294587135315,
+      "learning_rate": 9.771697127413562e-07,
+      "loss": 0.088,
+      "step": 200
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.10271219164133072,
+      "learning_rate": 9.094623563274826e-07,
+      "loss": 0.0871,
+      "step": 201
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.10967603325843811,
+      "learning_rate": 8.440971324455538e-07,
+      "loss": 0.0868,
+      "step": 202
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.10355532169342041,
+      "learning_rate": 7.810872496301524e-07,
+      "loss": 0.0871,
+      "step": 203
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.1027318611741066,
+      "learning_rate": 7.204454404654712e-07,
+      "loss": 0.0868,
+      "step": 204
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.10293618589639664,
+      "learning_rate": 6.621839590124038e-07,
+      "loss": 0.0894,
+      "step": 205
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.11122537404298782,
+      "learning_rate": 6.063145783323232e-07,
+      "loss": 0.0878,
+      "step": 206
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.10315720736980438,
+      "learning_rate": 5.528485881080792e-07,
+      "loss": 0.0865,
+      "step": 207
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.10112498700618744,
+      "learning_rate": 5.017967923626507e-07,
+      "loss": 0.0883,
+      "step": 208
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.10506224632263184,
+      "learning_rate": 4.5316950727595093e-07,
+      "loss": 0.0863,
+      "step": 209
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.09884654730558395,
+      "learning_rate": 4.0697655910021116e-07,
+      "loss": 0.0872,
+      "step": 210
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.10523875802755356,
+      "learning_rate": 3.6322728217434986e-07,
+      "loss": 0.0875,
+      "step": 211
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.10605299472808838,
+      "learning_rate": 3.2193051703777316e-07,
+      "loss": 0.0869,
+      "step": 212
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.10434259474277496,
+      "learning_rate": 2.8309460864393013e-07,
+      "loss": 0.0881,
+      "step": 213
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.10123943537473679,
+      "learning_rate": 2.467274046740256e-07,
+      "loss": 0.0858,
+      "step": 214
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.10703049600124359,
+      "learning_rate": 2.128362539512277e-07,
+      "loss": 0.0876,
+      "step": 215
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.1104775071144104,
+      "learning_rate": 1.814280049556555e-07,
+      "loss": 0.0899,
+      "step": 216
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.10637407749891281,
+      "learning_rate": 1.5250900444049866e-07,
+      "loss": 0.0889,
+      "step": 217
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.10246419161558151,
+      "learning_rate": 1.2608509614950305e-07,
+      "loss": 0.086,
+      "step": 218
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.10598447918891907,
+      "learning_rate": 1.0216161963611942e-07,
+      "loss": 0.0853,
+      "step": 219
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.0996188074350357,
+      "learning_rate": 8.074340918451245e-08,
+      "loss": 0.0868,
+      "step": 220
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.09922067075967789,
+      "learning_rate": 6.183479283269344e-08,
+      "loss": 0.0871,
+      "step": 221
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.1013500913977623,
+      "learning_rate": 4.5439591497933864e-08,
+      "loss": 0.0876,
+      "step": 222
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.10157408565282822,
+      "learning_rate": 3.156111820466906e-08,
+      "loss": 0.0851,
+      "step": 223
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.11184182018041611,
+      "learning_rate": 2.0202177415021284e-08,
+      "loss": 0.0869,
+      "step": 224
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.09960313141345978,
+      "learning_rate": 1.1365064462093289e-08,
+      "loss": 0.0856,
+      "step": 225
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.10157773643732071,
+      "learning_rate": 5.05156508614768e-09,
+      "loss": 0.0861,
+      "step": 226
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.0989537239074707,
+      "learning_rate": 1.2629550737580653e-09,
+      "loss": 0.0879,
+      "step": 227
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.10392510890960693,
+      "learning_rate": 0.0,
+      "loss": 0.0878,
+      "step": 228
+    },
+    {
+      "epoch": 2.0,
+      "step": 228,
+      "total_flos": 1.754512899115162e+19,
+      "train_loss": 0.11250041604957037,
+      "train_runtime": 28780.3034,
+      "train_samples_per_second": 12.195,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 1.754512899115162e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e760885b01ef7c802e215dbe61a244eb49157790494bbf2cefc92820ed9572
+size 7352