Re-add tokenizer.json tracked with LFS

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -1,24 +1,3 @@
-{
-  "</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,
-  "<|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
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
+size 605

chat_template.json

@@ -1,3 +1,3 @@
-{
-  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
+size 1049

config.json

@@ -1,53 +1,3 @@
-{
-  "_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
-  "architectures": [
-    "Qwen2_5_VLForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 2048,
-  "image_token_id": 151655,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 128000,
-  "max_window_layers": 70,
-  "model_type": "qwen2_5_vl",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 36,
-  "num_key_value_heads": 2,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "mrope_section": [
-      16,
-      24,
-      24
-    ],
-    "rope_type": "default",
-    "type": "default"
-  },
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": true,
-  "tokenizer_padding_side": "right",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
-  "use_sliding_window": false,
-  "video_token_id": 151656,
-  "vision_config": {
-    "hidden_size": 1280,
-    "in_chans": 3,
-    "model_type": "qwen2_5_vl",
-    "out_hidden_size": 2048,
-    "spatial_patch_size": 14,
-    "tokens_per_second": 2,
-    "torch_dtype": "bfloat16"
-  },
-  "vision_end_token_id": 151653,
-  "vision_lr": 2e-06,
-  "vision_start_token_id": 151652,
-  "vision_token_id": 151654,
-  "vocab_size": 151936
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:451db59d251da5cf466db038a8c7aa5cc8e0c05c301950efe996211f4cf1a7b1
+size 1306

generation_config.json

@@ -1,13 +1,3 @@
-{
-  "attn_implementation": "sdpa",
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 1e-06,
-  "transformers_version": "4.49.0.dev0"
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b70cbd07fa28a9b92042c82ce742a27b1aca3bbfc1b71c14b076dc87acf958
+size 252

model.safetensors.index.json

@@ -1,832 +1,3 @@
-{
-  "metadata": {
-    "total_size": 8131575808
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00002-of-00002.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors",
-    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
-    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
-    "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
-    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:4baae1a97d78a29dfc8f319663db6a20cdc85a84da3b3d869045f7ff9c76f501
+size 65506

preprocessor_config.json

@@ -1,29 +1,3 @@
-{
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_processor_type": "Qwen2_5_VLImageProcessor",
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "max_pixels": 12845056,
-  "merge_size": 2,
-  "min_pixels": 3136,
-  "patch_size": 14,
-  "processor_class": "Qwen2_5_VLProcessor",
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "max_pixels": 12845056,
-    "min_pixels": 3136
-  },
-  "temporal_patch_size": 2
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d55622ce2c010e1991233a47c138fccca18541721fba78dd43fd03180894e36
+size 573

special_tokens_map.json

@@ -1,31 +1,3 @@
-{
-  "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|>"
-  ],
-  "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
-  }
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
+size 613

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -1,210 +1,3 @@
-{
-  "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
-    }
-  },
-  "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|>"
-  ],
-  "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        {{- 'You are a helpful assistant.' }}\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\\nYou are a helpful assistant.<|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",
-  "extra_special_tokens": {},
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "processor_class": "Qwen2_5_VLProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1261bba2c7de85f22b3e45a90e4511f2dd4a72ea69d8eee808dfed241ebbb5a
+size 7327

trainer_state.json

@@ -1,159 +1,3 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.9959183673469387,
-  "eval_steps": 500,
-  "global_step": 183,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.05442176870748299,
-      "grad_norm": 10.409563064575195,
-      "learning_rate": 9.987404054446009e-06,
-      "loss": 1.1754,
-      "step": 10
-    },
-    {
-      "epoch": 0.10884353741496598,
-      "grad_norm": 18.703964233398438,
-      "learning_rate": 9.846427491892117e-06,
-      "loss": 0.0536,
-      "step": 20
-    },
-    {
-      "epoch": 0.16326530612244897,
-      "grad_norm": 0.051615361124277115,
-      "learning_rate": 9.553173864274567e-06,
-      "loss": 0.0095,
-      "step": 30
-    },
-    {
-      "epoch": 0.21768707482993196,
-      "grad_norm": 3.3554723262786865,
-      "learning_rate": 9.116857340547203e-06,
-      "loss": 0.0303,
-      "step": 40
-    },
-    {
-      "epoch": 0.272108843537415,
-      "grad_norm": 0.5499916672706604,
-      "learning_rate": 8.551187194145591e-06,
-      "loss": 0.0017,
-      "step": 50
-    },
-    {
-      "epoch": 0.32653061224489793,
-      "grad_norm": 0.03119831532239914,
-      "learning_rate": 7.873937051072037e-06,
-      "loss": 0.0005,
-      "step": 60
-    },
-    {
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.0163834560662508,
-      "learning_rate": 7.106386434082979e-06,
-      "loss": 0.0073,
-      "step": 70
-    },
-    {
-      "epoch": 0.43537414965986393,
-      "grad_norm": 2.7134735584259033,
-      "learning_rate": 6.272652149926989e-06,
-      "loss": 0.048,
-      "step": 80
-    },
-    {
-      "epoch": 0.4897959183673469,
-      "grad_norm": 10.595450401306152,
-      "learning_rate": 5.398930527765416e-06,
-      "loss": 0.0195,
-      "step": 90
-    },
-    {
-      "epoch": 0.54421768707483,
-      "grad_norm": 0.37698984146118164,
-      "learning_rate": 4.512674318006268e-06,
-      "loss": 0.0023,
-      "step": 100
-    },
-    {
-      "epoch": 0.5986394557823129,
-      "grad_norm": 0.10373763740062714,
-      "learning_rate": 3.641730113782807e-06,
-      "loss": 0.0006,
-      "step": 110
-    },
-    {
-      "epoch": 0.6530612244897959,
-      "grad_norm": 2.0312111377716064,
-      "learning_rate": 2.8134633977057236e-06,
-      "loss": 0.0127,
-      "step": 120
-    },
-    {
-      "epoch": 0.7074829931972789,
-      "grad_norm": 0.7092216610908508,
-      "learning_rate": 2.053898705337583e-06,
-      "loss": 0.0095,
-      "step": 130
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.36711186170578003,
-      "learning_rate": 1.3869019218635644e-06,
-      "loss": 0.0007,
-      "step": 140
-    },
-    {
-      "epoch": 0.8163265306122449,
-      "grad_norm": 0.18850086629390717,
-      "learning_rate": 8.334304045874248e-07,
-      "loss": 0.0017,
-      "step": 150
-    },
-    {
-      "epoch": 0.8707482993197279,
-      "grad_norm": 1.0802397727966309,
-      "learning_rate": 4.108744927617669e-07,
-      "loss": 0.0066,
-      "step": 160
-    },
-    {
-      "epoch": 0.9251700680272109,
-      "grad_norm": 0.890288233757019,
-      "learning_rate": 1.3251109482806667e-07,
-      "loss": 0.0008,
-      "step": 170
-    },
-    {
-      "epoch": 0.9795918367346939,
-      "grad_norm": 0.13776013255119324,
-      "learning_rate": 7.0865216161902785e-09,
-      "loss": 0.0006,
-      "step": 180
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 183,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 4.352668087825203e+16,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6130e9a6f102f5ed9b39be8a84750d90caf1bdfca6fa4d36e7ad0318b60d8f
+size 3878