Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|image|>": 151665,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,148 @@
+{
+  "_name_or_path": "URSA-8B-PS-GRPO",
+  "aligner_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cls": "MlpProjector",
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "aligner",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "params": {
+      "depth": 2,
+      "input_dim": 1024,
+      "n_embed": 3584,
+      "projector_type": "low_high_hybrid_split_mlp_gelu"
+    },
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "architectures": [
+    "UrsaForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_token_index": 151665,
+  "model_type": "ursa",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_size": 3584,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 4096,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_sliding_window": false,
+    "vocab_size": 152064
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "vision_config": {
+    "cls": "HybridVisionTower",
+    "model_type": "vision",
+    "params": {
+      "concat_type": "tuple",
+      "freeze_high": true,
+      "freeze_low": true,
+      "high_res_cfg": {
+        "ckpt_path": "",
+        "image_size": 1024,
+        "model_name": "sam_b_downsample",
+        "output_dim": 1024,
+        "pixel_mean": [
+          0.48145466,
+          0.4578275,
+          0.40821073
+        ],
+        "pixel_std": [
+          0.26862954,
+          0.26130258,
+          0.27577711
+        ],
+        "select_feature": "same",
+        "select_layer": -1
+      },
+      "low_res_cfg": {
+        "ckpt_path": "",
+        "image_size": 384,
+        "model_name": "siglip_large_patch16_384",
+        "output_dim": 1024,
+        "pixel_mean": [
+          0.5,
+          0.5,
+          0.5
+        ],
+        "pixel_std": [
+          0.5,
+          0.5,
+          0.5
+        ],
+        "select_feature": "same",
+        "select_layer": -1
+      }
+    }
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0236e1205629ed21db2afb354b764ded8968a6ae465283caf8bb87f25dba81
+size 4946419388

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb3a1c2494f7b8542b30784db29d8f733c7d817e11751a0e00f4aeaeba3cbee
+size 4932744848

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ec89acbdb981b8e18c8b4f5fb59e8fe250f3e4c822c3bb19e8cc4c4483d078
+size 4932744856

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95b8b6dc3a6ca97f1ac8f1bf3eff6e1608cbbddec78c1a1b6306a852368cdbaf
+size 4998853328

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616f80ce18a595139bfb8594fcce8e7c73846ad1e9d9f443874f48cd3cf14850
+size 4984125264

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88363566ce40c2e00f486d64b36ad5ed317ed12054e7d776cc112e31eb6dc74d
+size 4932744904

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d3bd768eedf155294d6002f4443dff1300f1b9c95fd01ff9d4a86307d73703
+size 2451614336

model.safetensors.index.json

@@ -0,0 +1,848 @@
+{
+  "metadata": {
+    "total_size": 32179133444
+  },
+  "weight_map": {
+    "aligner.high_up_proj.bias": "model-00001-of-00007.safetensors",
+    "aligner.high_up_proj.weight": "model-00001-of-00007.safetensors",
+    "aligner.layers.1.bias": "model-00001-of-00007.safetensors",
+    "aligner.layers.1.weight": "model-00001-of-00007.safetensors",
+    "aligner.low_up_proj.bias": "model-00001-of-00007.safetensors",
+    "aligner.low_up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.lm_head.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "language_model.model.norm.weight": "model-00007-of-00007.safetensors",
+    "vision_model.high_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "vision_model.high_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_model.low_layer_norm.bias": "model-00001-of-00007.safetensors",
+    "vision_model.low_layer_norm.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.0.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.1.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.10.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.11.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.2.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.3.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.4.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.5.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.6.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.7.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.8.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.rel_pos_h": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.attn.rel_pos_w": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.mlp.lin1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.mlp.lin1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.mlp.lin2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.mlp.lin2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.blocks.9.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.downsamples.0.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.downsamples.1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.hd_alpha_downsamples": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.0.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.3.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck.3.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.0.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.3.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.neck_hd.3.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.patch_embed.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.patch_embed.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_high.vision_tower.pos_embed": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.kv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.kv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.latent": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.norm.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.norm.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.q.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.attn_pool.q.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.0.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.1.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.10.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.11.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.12.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.13.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.14.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.15.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.16.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.17.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.18.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.19.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.2.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.20.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.21.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.22.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.23.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.3.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.4.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.5.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.6.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.7.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.8.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.norm1.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.norm1.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.norm2.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.blocks.9.norm2.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.norm.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.norm.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.patch_embed.proj.bias": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.patch_embed.proj.weight": "model-00001-of-00007.safetensors",
+    "vision_model.vision_tower_low.vision_tower.pos_embed": "model-00001-of-00007.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "background_color": [
+    122,
+    116,
+    104
+  ],
+  "do_normalize": false,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "VLMImageProcessor",
+  "image_size": 1024,
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "min_size": 14,
+  "processor_class": "Qwen2vlmProcessor",
+  "rescale_factor": 0.00392156862745098
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|image|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020dd2a3fab5170fa5e566be16a6792841f56bdb90660b8a2e2145ac92327e58
+size 11422082

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "add_bos_token": false,
+  "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|image|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2vlmProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9238578680203045,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04060913705583756,
+      "grad_norm": 2.231037139892578,
+      "learning_rate": 1e-05,
+      "loss": 0.6587,
+      "step": 1
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 2.3449997901916504,
+      "learning_rate": 2e-05,
+      "loss": 0.7422,
+      "step": 2
+    },
+    {
+      "epoch": 0.1218274111675127,
+      "grad_norm": 1.36476731300354,
+      "learning_rate": 1.9989930665413148e-05,
+      "loss": 0.5462,
+      "step": 3
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 1.2183294296264648,
+      "learning_rate": 1.9959742939952393e-05,
+      "loss": 0.52,
+      "step": 4
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 0.9061247706413269,
+      "learning_rate": 1.990949761767935e-05,
+      "loss": 0.5118,
+      "step": 5
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 0.8054011464118958,
+      "learning_rate": 1.98392958859863e-05,
+      "loss": 0.4539,
+      "step": 6
+    },
+    {
+      "epoch": 0.28426395939086296,
+      "grad_norm": 0.7858198881149292,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.4697,
+      "step": 7
+    },
+    {
+      "epoch": 0.3248730964467005,
+      "grad_norm": 0.7081526517868042,
+      "learning_rate": 1.9639628606958535e-05,
+      "loss": 0.4,
+      "step": 8
+    },
+    {
+      "epoch": 0.36548223350253806,
+      "grad_norm": 0.7763380408287048,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.4542,
+      "step": 9
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 0.6853049993515015,
+      "learning_rate": 1.9362348706397374e-05,
+      "loss": 0.4059,
+      "step": 10
+    },
+    {
+      "epoch": 0.4467005076142132,
+      "grad_norm": 0.7308188676834106,
+      "learning_rate": 1.919527772551451e-05,
+      "loss": 0.4162,
+      "step": 11
+    },
+    {
+      "epoch": 0.4873096446700508,
+      "grad_norm": 0.7724586129188538,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.4469,
+      "step": 12
+    },
+    {
+      "epoch": 0.5279187817258884,
+      "grad_norm": 0.6326901316642761,
+      "learning_rate": 1.880595531856738e-05,
+      "loss": 0.422,
+      "step": 13
+    },
+    {
+      "epoch": 0.5685279187817259,
+      "grad_norm": 0.6398388147354126,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 0.4343,
+      "step": 14
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 0.5947191715240479,
+      "learning_rate": 1.834573253721303e-05,
+      "loss": 0.3745,
+      "step": 15
+    },
+    {
+      "epoch": 0.649746192893401,
+      "grad_norm": 0.6309987306594849,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.3943,
+      "step": 16
+    },
+    {
+      "epoch": 0.6903553299492385,
+      "grad_norm": 0.6212602853775024,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.3954,
+      "step": 17
+    },
+    {
+      "epoch": 0.7309644670050761,
+      "grad_norm": 0.6566072702407837,
+      "learning_rate": 1.7530714660036112e-05,
+      "loss": 0.3788,
+      "step": 18
+    },
+    {
+      "epoch": 0.7715736040609137,
+      "grad_norm": 0.6458687782287598,
+      "learning_rate": 1.7227948638273918e-05,
+      "loss": 0.3884,
+      "step": 19
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 0.6482535004615784,
+      "learning_rate": 1.691062648986865e-05,
+      "loss": 0.4218,
+      "step": 20
+    },
+    {
+      "epoch": 0.8527918781725888,
+      "grad_norm": 0.6024514436721802,
+      "learning_rate": 1.657938725939713e-05,
+      "loss": 0.4183,
+      "step": 21
+    },
+    {
+      "epoch": 0.8934010152284264,
+      "grad_norm": 0.6119846105575562,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.3988,
+      "step": 22
+    },
+    {
+      "epoch": 0.934010152284264,
+      "grad_norm": 0.5902426838874817,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.3743,
+      "step": 23
+    },
+    {
+      "epoch": 0.9746192893401016,
+      "grad_norm": 0.5760794878005981,
+      "learning_rate": 1.5508969814521026e-05,
+      "loss": 0.385,
+      "step": 24
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 0.5974088907241821,
+      "learning_rate": 1.5128992774059063e-05,
+      "loss": 0.3249,
+      "step": 25
+    },
+    {
+      "epoch": 1.0558375634517767,
+      "grad_norm": 0.44053706526756287,
+      "learning_rate": 1.4738686624729987e-05,
+      "loss": 0.2409,
+      "step": 26
+    },
+    {
+      "epoch": 1.0964467005076142,
+      "grad_norm": 0.46850693225860596,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.2628,
+      "step": 27
+    },
+    {
+      "epoch": 1.1370558375634519,
+      "grad_norm": 0.47877609729766846,
+      "learning_rate": 1.3930250316539237e-05,
+      "loss": 0.248,
+      "step": 28
+    },
+    {
+      "epoch": 1.1776649746192893,
+      "grad_norm": 0.503269374370575,
+      "learning_rate": 1.3513748240813429e-05,
+      "loss": 0.2306,
+      "step": 29
+    },
+    {
+      "epoch": 1.218274111675127,
+      "grad_norm": 0.4539880156517029,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.2199,
+      "step": 30
+    },
+    {
+      "epoch": 1.2588832487309645,
+      "grad_norm": 0.6157008409500122,
+      "learning_rate": 1.2660368455666752e-05,
+      "loss": 0.2287,
+      "step": 31
+    },
+    {
+      "epoch": 1.299492385786802,
+      "grad_norm": 0.4458495080471039,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.2238,
+      "step": 32
+    },
+    {
+      "epoch": 1.3401015228426396,
+      "grad_norm": 0.44391369819641113,
+      "learning_rate": 1.1785568947986368e-05,
+      "loss": 0.215,
+      "step": 33
+    },
+    {
+      "epoch": 1.380710659898477,
+      "grad_norm": 0.46967068314552307,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 0.2079,
+      "step": 34
+    },
+    {
+      "epoch": 1.4213197969543148,
+      "grad_norm": 0.44738730788230896,
+      "learning_rate": 1.0896393089034336e-05,
+      "loss": 0.2095,
+      "step": 35
+    },
+    {
+      "epoch": 1.4619289340101522,
+      "grad_norm": 0.438690721988678,
+      "learning_rate": 1.044864830350515e-05,
+      "loss": 0.2081,
+      "step": 36
+    },
+    {
+      "epoch": 1.50253807106599,
+      "grad_norm": 0.43093299865722656,
+      "learning_rate": 1e-05,
+      "loss": 0.1841,
+      "step": 37
+    },
+    {
+      "epoch": 1.5431472081218274,
+      "grad_norm": 0.47970595955848694,
+      "learning_rate": 9.551351696494854e-06,
+      "loss": 0.2152,
+      "step": 38
+    },
+    {
+      "epoch": 1.5837563451776648,
+      "grad_norm": 0.4089057147502899,
+      "learning_rate": 9.103606910965666e-06,
+      "loss": 0.1878,
+      "step": 39
+    },
+    {
+      "epoch": 1.6243654822335025,
+      "grad_norm": 0.4573724567890167,
+      "learning_rate": 8.657667341823449e-06,
+      "loss": 0.1955,
+      "step": 40
+    },
+    {
+      "epoch": 1.6649746192893402,
+      "grad_norm": 0.46062809228897095,
+      "learning_rate": 8.214431052013636e-06,
+      "loss": 0.1898,
+      "step": 41
+    },
+    {
+      "epoch": 1.7055837563451777,
+      "grad_norm": 0.47705650329589844,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.2261,
+      "step": 42
+    },
+    {
+      "epoch": 1.7461928934010151,
+      "grad_norm": 0.4647163450717926,
+      "learning_rate": 7.33963154433325e-06,
+      "loss": 0.1794,
+      "step": 43
+    },
+    {
+      "epoch": 1.7868020304568528,
+      "grad_norm": 0.47383496165275574,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.1966,
+      "step": 44
+    },
+    {
+      "epoch": 1.8274111675126905,
+      "grad_norm": 0.4777352511882782,
+      "learning_rate": 6.486251759186573e-06,
+      "loss": 0.1909,
+      "step": 45
+    },
+    {
+      "epoch": 1.868020304568528,
+      "grad_norm": 0.5107164978981018,
+      "learning_rate": 6.069749683460765e-06,
+      "loss": 0.2004,
+      "step": 46
+    },
+    {
+      "epoch": 1.9086294416243654,
+      "grad_norm": 1.4848881959915161,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.1932,
+      "step": 47
+    },
+    {
+      "epoch": 1.9492385786802031,
+      "grad_norm": 0.43872544169425964,
+      "learning_rate": 5.2613133752700145e-06,
+      "loss": 0.1874,
+      "step": 48
+    },
+    {
+      "epoch": 1.9898477157360406,
+      "grad_norm": 0.5519695281982422,
+      "learning_rate": 4.87100722594094e-06,
+      "loss": 0.1995,
+      "step": 49
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 0.4047316610813141,
+      "learning_rate": 4.491030185478976e-06,
+      "loss": 0.1541,
+      "step": 50
+    },
+    {
+      "epoch": 2.0710659898477157,
+      "grad_norm": 0.39870932698249817,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.1425,
+      "step": 51
+    },
+    {
+      "epoch": 2.1116751269035534,
+      "grad_norm": 0.3946266174316406,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.1455,
+      "step": 52
+    },
+    {
+      "epoch": 2.152284263959391,
+      "grad_norm": 0.37286555767059326,
+      "learning_rate": 3.4206127406028744e-06,
+      "loss": 0.127,
+      "step": 53
+    },
+    {
+      "epoch": 2.1928934010152283,
+      "grad_norm": 0.3995823264122009,
+      "learning_rate": 3.089373510131354e-06,
+      "loss": 0.1484,
+      "step": 54
+    },
+    {
+      "epoch": 2.233502538071066,
+      "grad_norm": 0.3770010471343994,
+      "learning_rate": 2.7720513617260857e-06,
+      "loss": 0.1344,
+      "step": 55
+    },
+    {
+      "epoch": 2.2741116751269037,
+      "grad_norm": 0.36149802803993225,
+      "learning_rate": 2.469285339963892e-06,
+      "loss": 0.1243,
+      "step": 56
+    },
+    {
+      "epoch": 2.314720812182741,
+      "grad_norm": 0.36556974053382874,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.1271,
+      "step": 57
+    },
+    {
+      "epoch": 2.3553299492385786,
+      "grad_norm": 0.3600409924983978,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1233,
+      "step": 58
+    },
+    {
+      "epoch": 2.3959390862944163,
+      "grad_norm": 0.3835366368293762,
+      "learning_rate": 1.6542674627869738e-06,
+      "loss": 0.1194,
+      "step": 59
+    },
+    {
+      "epoch": 2.436548223350254,
+      "grad_norm": 0.38183608651161194,
+      "learning_rate": 1.4155120639813392e-06,
+      "loss": 0.1407,
+      "step": 60
+    },
+    {
+      "epoch": 2.4771573604060912,
+      "grad_norm": 0.3950784206390381,
+      "learning_rate": 1.19404468143262e-06,
+      "loss": 0.1265,
+      "step": 61
+    },
+    {
+      "epoch": 2.517766497461929,
+      "grad_norm": 0.47062575817108154,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.1124,
+      "step": 62
+    },
+    {
+      "epoch": 2.5583756345177666,
+      "grad_norm": 0.40783652663230896,
+      "learning_rate": 8.047222744854943e-07,
+      "loss": 0.1381,
+      "step": 63
+    },
+    {
+      "epoch": 2.598984771573604,
+      "grad_norm": 0.45733270049095154,
+      "learning_rate": 6.37651293602628e-07,
+      "loss": 0.1211,
+      "step": 64
+    },
+    {
+      "epoch": 2.6395939086294415,
+      "grad_norm": 0.3771652579307556,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.1161,
+      "step": 65
+    },
+    {
+      "epoch": 2.6802030456852792,
+      "grad_norm": 0.38524389266967773,
+      "learning_rate": 3.603713930414676e-07,
+      "loss": 0.1191,
+      "step": 66
+    },
+    {
+      "epoch": 2.720812182741117,
+      "grad_norm": 0.3731960356235504,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.1071,
+      "step": 67
+    },
+    {
+      "epoch": 2.761421319796954,
+      "grad_norm": 0.4229435920715332,
+      "learning_rate": 1.6070411401370335e-07,
+      "loss": 0.1267,
+      "step": 68
+    },
+    {
+      "epoch": 2.802030456852792,
+      "grad_norm": 0.3722592294216156,
+      "learning_rate": 9.0502382320653e-08,
+      "loss": 0.1235,
+      "step": 69
+    },
+    {
+      "epoch": 2.8426395939086295,
+      "grad_norm": 0.4112900495529175,
+      "learning_rate": 4.025706004760932e-08,
+      "loss": 0.1173,
+      "step": 70
+    },
+    {
+      "epoch": 2.8832487309644668,
+      "grad_norm": 0.35562577843666077,
+      "learning_rate": 1.0069334586854106e-08,
+      "loss": 0.1143,
+      "step": 71
+    },
+    {
+      "epoch": 2.9238578680203045,
+      "grad_norm": 0.427130788564682,
+      "learning_rate": 0.0,
+      "loss": 0.1234,
+      "step": 72
+    },
+    {
+      "epoch": 2.9238578680203045,
+      "step": 72,
+      "total_flos": 1.856511114477568e+16,
+      "train_loss": 0.2654210272141629,
+      "train_runtime": 1195.1529,
+      "train_samples_per_second": 7.902,
+      "train_steps_per_second": 0.06
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 72,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 26,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.856511114477568e+16,
+  "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 sha256:692c26c0bf7c477b8d066681651bd6011db5ae8b5c6c48a74107b8e67ced4c0c
+size 5752