Upload checkpoint folder experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15

.gitattributes

@@ -2168,3 +2168,4 @@ experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3
 experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_105/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 experiments/weak_to_strong/agent/baseline/260920-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-sysv1-step150-4gpu-fp32/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 experiments/weak_to_strong/agent/ours/260920-pixel-qwen25vl-7b-warmstart-oprd-t3b-step90-lp0p5-lm0to0p5-s45-b64-mb64-n8-sysv1-step150-4gpu-fp32-toolmatch-v2/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29d852168249f50ae4e87bee464d85ae91732ee4ae8e91bbd41ac26fdcd78bb
+size 15141

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3d7680fbe0f76e3d81e796077e27f266ac98d7dae4c2720f68da46639640b3
+size 15141

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c25fbc60bdd418746f9935d5be9aff796c3501a815e2426a3b1bc2cfcdf50c
+size 15141

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/extra_state_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0836382c9e750819fdfe74f10c47decff207f8c30c968865bd49e02641d235d
+size 15141

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 4
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</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
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/config.json

@@ -0,0 +1,133 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "/NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/local_hf/pixelreasoner-7b-sft",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float32",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "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": "4.57.1",
+  "use_cache": false
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5895132a5938155fef9c7fe98dfbca740d406da2db7dbf947a6e00dc997b8de3
+size 4952311608

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f12f432daa9834b9094f4ebecb46cea795e3e755b99007b4e75504491d44578e
+size 4984124272

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bfcd7ed4a5b46c6ce3336b7206f65ea0d4ac23cc006924929e61b16e2aaebf
+size 4932743936

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0d3fff577b03eeda4e99ac01a1120c74c3dce77915f083737a7daef8fd45be
+size 4998852296

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f414c6150ce47de8db9b4e95e3eb22b4558881c0ac7d88e37169f33bea9e79c
+size 4984124336

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6305fbaf48590bbc4209fedae1b97519805f5a45dba2dafa883f6bbe777b5e54
+size 4932743992

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdee284fcb3a3984912e6623d17a8acbcced5c8340e6c65747714af1e92c3fd
+size 3383846800

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+  "metadata": {
+    "total_parameters": 8292166656,
+    "total_size": 33168666624
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00007.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00007.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00007.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00007.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00007.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00007.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00007.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00007.safetensors"
+  }
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 4014080,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 4014080,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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
+  }
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/tokenizer.json

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

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/huggingface/video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 4014080,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 4014080,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90da7a3389f334f1720db69ad934e0efd5eb73632fcb670ac1980e9394a4693
+size 8292577683

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2b49eea8a018cda7c52fd505b77ad3c9da71d80715bc657845d7f555122ad5
+size 8292577683

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b151361d585037a043a216c4c59ace609ece1e08dc016ada3eef531a14f568
+size 8292577683

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/model_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd4678c4780211f7e3053092aaa0761968b86dda9cd521636afea1f987fb558
+size 8292577683

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de6c630691fc60809e8ac8c8e90de726d590f68fec57f1bba755c5cda938605
+size 16584501731

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c0e76ea49015efc7b13ed2fab71defc065cac9cfe7001214258ec805364192
+size 16584501731

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100a9c70917d2bc2ac5787bb7b6eea949507915904ae24087538fc0f2ac42ab2
+size 16584501731

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/actor/optim_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e69b9e3188b2c94655f72827b15954bedeb82f325f44d54cd68b44556514094
+size 16584501731

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d503f1b6ed6a457c5a9ee9b41bdee0fa8ad4031814d6d5ed87f0937041144635
+size 1755

experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/global_step_15/resolved_config.yaml

@@ -0,0 +1,633 @@
+actor_rollout_ref:
+  actor:
+    optim:
+      _target_: verl.workers.config.FSDPOptimizerConfig
+      optimizer: AdamW
+      optimizer_impl: torch.optim
+      lr: 1.0e-06
+      lr_warmup_steps_ratio: 0.0
+      total_training_steps: 150
+      weight_decay: 0.01
+      lr_warmup_steps: 10
+      betas:
+      - 0.9
+      - 0.999
+      clip_grad: 1.0
+      min_lr_ratio: 0.0
+      num_cycles: 0.5
+      lr_scheduler_type: constant
+      warmup_style: null
+      override_optimizer_config:
+        foreach: false
+    fsdp_config:
+      _target_: verl.workers.config.FSDPEngineConfig
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      optimizer_offload: false
+      offload_policy: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+      model_dtype: fp32
+      use_orig_params: false
+      ulysses_sequence_parallel_size: 1
+      entropy_from_logits_with_chunking: false
+      use_torch_compile: true
+      entropy_checkpointing: false
+      forward_only: false
+      strategy: fsdp
+      mixed_precision:
+        param_dtype: bf16
+        reduce_dtype: fp32
+        buffer_dtype: fp32
+    _target_: verl.workers.config.FSDPActorConfig
+    strategy: fsdp
+    ppo_mini_batch_size: 64
+    ppo_micro_batch_size: null
+    ppo_micro_batch_size_per_gpu: 2
+    use_dynamic_bsz: false
+    ppo_max_token_len_per_gpu: 16384
+    clip_ratio: 0.2
+    clip_ratio_low: 0.2
+    clip_ratio_high: 0.28
+    freeze_vision_tower: false
+    policy_loss:
+      _target_: verl.workers.config.PolicyLossConfig
+      loss_mode: vanilla
+      clip_cov_ratio: 0.0002
+      clip_cov_lb: 1.0
+      clip_cov_ub: 5.0
+      kl_cov_ratio: 0.0002
+      ppo_kl_coef: 0.1
+    clip_ratio_c: 3.0
+    loss_agg_mode: token-mean
+    entropy_coeff: 0.0
+    use_kl_loss: false
+    use_torch_compile: true
+    kl_loss_coef: 0.0
+    kl_loss_type: low_var_kl
+    ppo_epochs: 1
+    shuffle: false
+    checkpoint:
+      _target_: verl.trainer.config.CheckpointConfig
+      save_contents:
+      - model
+      - optimizer
+      - extra
+      - hf_model
+      load_contents:
+      - model
+      - optimizer
+      - extra
+      - hf_model
+      async_save: false
+    use_fused_kernels: false
+    profiler:
+      _target_: verl.utils.profiler.ProfilerConfig
+      tool: null
+      enable: false
+      all_ranks: false
+      ranks: []
+      save_path: outputs/profile
+      tool_config:
+        nsys:
+          _target_: verl.utils.profiler.config.NsightToolConfig
+          discrete: false
+        npu:
+          _target_: verl.utils.profiler.config.NPUToolConfig
+          contents: []
+          level: level1
+          analysis: true
+          discrete: false
+        torch:
+          _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+          step_start: 0
+          step_end: null
+        torch_memory:
+          _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+          trace_alloc_max_entries: 100000
+          stack_depth: 32
+    grad_clip: 1.0
+    ulysses_sequence_parallel_size: 1
+    entropy_from_logits_with_chunking: false
+    entropy_checkpointing: false
+    use_remove_padding: true
+  ref:
+    strategy: fsdp
+    use_torch_compile: true
+    log_prob_micro_batch_size: null
+    log_prob_micro_batch_size_per_gpu: null
+    log_prob_use_dynamic_bsz: false
+    log_prob_max_token_len_per_gpu: 16384
+    profiler:
+      _target_: verl.utils.profiler.ProfilerConfig
+      tool: null
+      enable: false
+      all_ranks: false
+      ranks: []
+      save_path: outputs/profile
+      tool_config:
+        nsys:
+          _target_: verl.utils.profiler.config.NsightToolConfig
+          discrete: false
+        npu:
+          _target_: verl.utils.profiler.config.NPUToolConfig
+          contents: []
+          level: level1
+          analysis: true
+          discrete: false
+        torch:
+          _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+          step_start: 0
+          step_end: null
+        torch_memory:
+          _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+          trace_alloc_max_entries: 100000
+          stack_depth: 32
+    fsdp_config:
+      _target_: verl.workers.config.FSDPEngineConfig
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      optimizer_offload: false
+      offload_policy: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+      model_dtype: fp32
+      use_orig_params: false
+      ulysses_sequence_parallel_size: 1
+      entropy_from_logits_with_chunking: false
+      use_torch_compile: true
+      entropy_checkpointing: false
+      forward_only: false
+      strategy: fsdp
+    model: null
+    ulysses_sequence_parallel_size: 1
+    entropy_from_logits_with_chunking: false
+    entropy_checkpointing: false
+  rollout:
+    _target_: verl.workers.config.RolloutConfig
+    name: vllm
+    mode: async
+    temperature: 1.0
+    top_k: -1
+    top_p: 1.0
+    prompt_length: 18432
+    response_length: 16384
+    dtype: bfloat16
+    gpu_memory_utilization: 0.5
+    ignore_eos: false
+    enforce_eager: true
+    cudagraph_capture_sizes: null
+    free_cache_engine: true
+    tensor_model_parallel_size: 1
+    data_parallel_size: 1
+    expert_parallel_size: 1
+    pipeline_model_parallel_size: 1
+    max_num_batched_tokens: 8192
+    max_model_len: 32768
+    max_num_seqs: 24
+    enable_chunked_prefill: true
+    enable_prefix_caching: false
+    load_format: dummy
+    log_prob_micro_batch_size: null
+    log_prob_micro_batch_size_per_gpu: 2
+    log_prob_use_dynamic_bsz: false
+    log_prob_max_token_len_per_gpu: 16384
+    disable_log_stats: true
+    do_sample: true
+    'n': 8
+    over_sample_rate: 0
+    multi_stage_wake_up: false
+    engine_kwargs:
+      vllm:
+        seed: 42
+        mm_processor_cache_gb: 0
+      sglang: {}
+    val_kwargs:
+      _target_: verl.workers.config.SamplingConfig
+      top_k: 20
+      top_p: 0.95
+      temperature: 0.6
+      'n': 1
+      do_sample: true
+    multi_turn:
+      _target_: verl.workers.config.MultiTurnConfig
+      enable: false
+      max_assistant_turns: null
+      tool_config_path: null
+      max_user_turns: null
+      max_parallel_calls: 1
+      max_tool_response_length: 256
+      tool_response_truncate_side: middle
+      interaction_config_path: null
+      use_inference_chat_template: false
+      tokenization_sanity_check_mode: strict
+      format: hermes
+      num_repeat_rollouts: null
+    calculate_log_probs: false
+    agent:
+      _target_: verl.workers.config.AgentLoopConfig
+      num_workers: 1
+      default_agent_loop: verltool_agent
+      agent_loop_config_path: null
+      custom_async_server:
+        _target_: verl.workers.config.CustomAsyncServerConfig
+        path: null
+        name: null
+    update_weights_bucket_megabytes: 512
+    trace:
+      _target_: verl.workers.config.TraceConfig
+      backend: null
+      token2text: false
+    skip_rollout: false
+    skip_dump_dir: /tmp/rollout_dump
+    skip_tokenizer_init: false
+    profiler:
+      _target_: verl.utils.profiler.ProfilerConfig
+      tool: null
+      enable: false
+      all_ranks: false
+      ranks: []
+      save_path: outputs/profile
+      tool_config:
+        nsys:
+          _target_: verl.utils.profiler.config.NsightToolConfig
+          discrete: false
+        npu:
+          _target_: verl.utils.profiler.config.NPUToolConfig
+          contents: []
+          level: level1
+          analysis: true
+          discrete: false
+        torch:
+          _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+          step_start: 0
+          step_end: null
+        torch_memory:
+          _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+          trace_alloc_max_entries: 100000
+          stack_depth: 32
+    layered_summon: false
+  model:
+    _target_: verl.workers.config.HFModelConfig
+    path: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/local_hf/pixelreasoner-7b-sft
+    hf_config_path: null
+    tokenizer_path: null
+    use_shm: false
+    trust_remote_code: false
+    custom_chat_template: null
+    external_lib: null
+    override_config:
+      attn_implementation: flash_attention_2
+    enable_gradient_checkpointing: true
+    enable_activation_offload: false
+    use_remove_padding: true
+    lora_rank: 0
+    lora_alpha: 16
+    target_modules: all-linear
+    exclude_modules: null
+    lora_adapter_path: null
+    use_liger: false
+    use_fused_kernels: false
+    fused_kernel_options:
+      impl_backend: torch
+  agent:
+    enable_agent: true
+    max_turns: 3
+    val_max_turns: 5
+    min_turns: 0
+    max_start_length: 18432
+    max_prompt_length: 18432
+    max_response_length: 16384
+    train_max_response_length: 16384
+    val_max_response_length: 16384
+    max_model_len: 32768
+    max_obs_length: 8192
+    max_action_length: 4096
+    val_max_action_length: 4096
+    eval_seed: 42
+    tool_server_url: http://127.0.0.1:30812/get_observation
+    'n': 8
+    truncate_obs_side: left
+    truncate_response_side: left
+    rolling_with_prompt: false
+    call_tool_first: false
+    action_stop_tokens: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/checkpoints/experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/action_stop_tokens.txt
+    additional_eos_token_ids: null
+    mask_observations: true
+    force_finish_for_last_turn: false
+    enable_mtrl: true
+    mtrl_role: user
+    mtrl_sep: null
+    turn_end_token: <|im_end|>
+    rollout_mode: async
+    mask_overlong_loss: false
+    max_concurrent_trajectories: 64
+    tool_call_timeout: 120
+  hybrid_engine: true
+  nccl_timeout: 600
+data:
+  tokenizer: null
+  use_shm: false
+  train_files:
+  - /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/datasets/pixel_agent_normalized_source_v1/train.parquet
+  val_files:
+  - /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/datasets/pixel_agent_normalized_source_v1/pixel_val.parquet
+  train_max_samples: -1
+  val_max_samples: -1
+  prompt_key: prompt
+  reward_fn_key: data_source
+  max_prompt_length: 18432
+  max_response_length: 16384
+  train_batch_size: 64
+  val_batch_size: 8
+  tool_config_path: null
+  return_raw_input_ids: true
+  return_raw_chat: true
+  return_full_prompt: false
+  shuffle: true
+  seed: 42
+  dataloader_num_workers: 2
+  image_patch_size: 14
+  validation_shuffle: false
+  filter_overlong_prompts: false
+  filter_overlong_prompts_workers: 1
+  truncation: error
+  image_key: images
+  video_key: videos
+  trust_remote_code: false
+  custom_cls:
+    path: null
+    name: null
+  return_multi_modal_inputs: false
+  sampler:
+    class_path: null
+    class_name: null
+  datagen:
+    path: null
+    name: null
+  apply_chat_template_kwargs: {}
+critic:
+  optim:
+    _target_: verl.workers.config.FSDPOptimizerConfig
+    optimizer: AdamW
+    optimizer_impl: torch.optim
+    lr: 1.0e-05
+    lr_warmup_steps_ratio: 0.0
+    total_training_steps: 150
+    weight_decay: 0.01
+    lr_warmup_steps: -1
+    betas:
+    - 0.9
+    - 0.999
+    clip_grad: 1.0
+    min_lr_ratio: 0.0
+    num_cycles: 0.5
+    lr_scheduler_type: constant
+    warmup_style: null
+    override_optimizer_config: null
+  model:
+    fsdp_config:
+      _target_: verl.workers.config.FSDPEngineConfig
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      optimizer_offload: false
+      offload_policy: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+      model_dtype: fp32
+      use_orig_params: false
+      ulysses_sequence_parallel_size: 1
+      entropy_from_logits_with_chunking: false
+      use_torch_compile: true
+      entropy_checkpointing: false
+      forward_only: false
+      strategy: fsdp
+    path: ~/models/deepseek-llm-7b-chat
+    tokenizer_path: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/local_hf/pixelreasoner-7b-sft
+    override_config: {}
+    external_lib: null
+    trust_remote_code: false
+    _target_: verl.workers.config.FSDPCriticModelCfg
+    use_shm: false
+    enable_gradient_checkpointing: true
+    enable_activation_offload: false
+    use_remove_padding: false
+    lora_rank: 0
+    lora_alpha: 16
+    target_modules: all-linear
+  _target_: verl.workers.config.FSDPCriticConfig
+  rollout_n: 8
+  strategy: fsdp
+  enable: null
+  ppo_mini_batch_size: 64
+  ppo_micro_batch_size: null
+  ppo_micro_batch_size_per_gpu: null
+  use_dynamic_bsz: false
+  ppo_max_token_len_per_gpu: 32768
+  forward_max_token_len_per_gpu: 32768
+  ppo_epochs: 1
+  shuffle: false
+  cliprange_value: 0.5
+  loss_agg_mode: token-mean
+  checkpoint:
+    _target_: verl.trainer.config.CheckpointConfig
+    save_contents:
+    - model
+    - optimizer
+    - extra
+    load_contents:
+    - model
+    - optimizer
+    - extra
+    async_save: false
+  profiler:
+    _target_: verl.utils.profiler.ProfilerConfig
+    tool: null
+    enable: false
+    all_ranks: false
+    ranks: []
+    save_path: outputs/profile
+    tool_config:
+      nsys:
+        _target_: verl.utils.profiler.config.NsightToolConfig
+        discrete: false
+      npu:
+        _target_: verl.utils.profiler.config.NPUToolConfig
+        contents: []
+        level: level1
+        analysis: true
+        discrete: false
+      torch:
+        _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+        step_start: 0
+        step_end: null
+      torch_memory:
+        _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+        trace_alloc_max_entries: 100000
+        stack_depth: 32
+  forward_micro_batch_size: null
+  forward_micro_batch_size_per_gpu: null
+  ulysses_sequence_parallel_size: 1
+  grad_clip: 1.0
+reward_model:
+  enable: false
+  enable_resource_pool: false
+  n_gpus_per_node: 0
+  nnodes: 0
+  strategy: fsdp
+  model:
+    input_tokenizer: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/local_hf/pixelreasoner-7b-sft
+    path: ~/models/FsfairX-LLaMA3-RM-v0.1
+    external_lib: null
+    trust_remote_code: false
+    use_shm: false
+    use_remove_padding: false
+    use_fused_kernels: false
+    fsdp_config:
+      _target_: verl.workers.config.FSDPEngineConfig
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+  micro_batch_size: null
+  micro_batch_size_per_gpu: null
+  max_length: null
+  use_dynamic_bsz: false
+  forward_max_token_len_per_gpu: 32768
+  reward_manager: pixel_reasoner_spec
+  launch_reward_fn_async: false
+  sandbox_fusion:
+    url: null
+    max_concurrent: 64
+    memory_limit_mb: 1024
+  profiler:
+    _target_: verl.utils.profiler.ProfilerConfig
+    tool: null
+    enable: false
+    all_ranks: false
+    ranks: []
+    save_path: outputs/profile
+    tool_config:
+      nsys:
+        _target_: verl.utils.profiler.config.NsightToolConfig
+        discrete: false
+      npu:
+        _target_: verl.utils.profiler.config.NPUToolConfig
+        contents: []
+        level: level1
+        analysis: true
+        discrete: false
+      torch:
+        _target_: verl.utils.profiler.config.TorchProfilerToolConfig
+        step_start: 0
+        step_end: null
+      torch_memory:
+        _target_: verl.utils.profiler.config.TorchMemoryToolConfig
+        trace_alloc_max_entries: 100000
+        stack_depth: 32
+  ulysses_sequence_parallel_size: 1
+custom_reward_function:
+  path: null
+  name: compute_score
+algorithm:
+  _target_: verl.trainer.config.AlgoConfig
+  gamma: 1.0
+  lam: 1.0
+  adv_estimator: grpo
+  norm_adv_by_std_in_grpo: false
+  use_kl_in_reward: false
+  kl_penalty: kl
+  kl_ctrl:
+    _target_: verl.trainer.config.KLControlConfig
+    type: fixed
+    kl_coef: 0.0
+    horizon: 10000
+    target_kl: 0.1
+  use_pf_ppo: false
+  pf_ppo:
+    reweight_method: pow
+    weight_pow: 2.0
+  rollout_is_threshold: null
+  rollout_is_threshold_lower: null
+  rollout_is_level: token
+  rollout_is_mode: truncate
+  rollout_is_veto_threshold: null
+  rollout_is: false
+trainer:
+  balance_batch: true
+  total_epochs: 150
+  total_training_steps: 150
+  project_name: weak_to_strong
+  experiment_name: weak-to-strong-agent-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32
+  logger:
+  - console
+  - wandb
+  log_val_generations: 1
+  rollout_data_dir: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/checkpoints/experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/rollouts
+  validation_data_dir: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/checkpoints/experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32/evaluation
+  nnodes: 1
+  n_gpus_per_node: 4
+  save_freq: 15
+  esi_redundant_time: 0
+  resume_mode: auto
+  resume_from_path: null
+  val_before_train: true
+  val_only: false
+  test_freq: 15
+  critic_warmup: 0
+  default_hdfs_dir: null
+  del_local_ckpt_after_load: false
+  default_local_dir: /NHNHOME/WORKSPACE/26msit001_A/sangmin/reverse_distill/distill/checkpoints/experiments/weak_to_strong/agent/baseline/260921-pixel-qwen25vl-7b-warmstart-grpo-b64-mb64-n8-normalized-source-v1-turn4k-step150-4gpu-fp32
+  max_actor_ckpt_to_keep: null
+  max_critic_ckpt_to_keep: null
+  ray_wait_register_center_timeout: 300
+  device: cuda
+  use_legacy_worker_impl: auto
+  pixel_preserve_checkpoint_every: 30
+  pixel_model_size: 7b
+  pixel_hf_auto_upload: true
+  pixel_hf_repo_id: yr-park/reverse_distill_assets
+  pixel_hf_repo_type: model
+  pixel_hf_async_upload: true
+global_profiler:
+  _target_: verl.utils.profiler.ProfilerConfig
+  tool: null
+  steps: null
+  profile_continuous_steps: false
+  save_path: outputs/profile
+  global_tool_config:
+    nsys:
+      _target_: verl.utils.profiler.config.NsightToolConfig
+      discrete: false
+      controller_nsight_options:
+        trace: cuda,nvtx,cublas,ucx
+        cuda-memory-usage: 'true'
+        cuda-graph-trace: graph
+      worker_nsight_options:
+        trace: cuda,nvtx,cublas,ucx
+        cuda-memory-usage: 'true'
+        cuda-graph-trace: graph
+        capture-range: cudaProfilerApi
+        capture-range-end: null
+        kill: none
+    torch_memory:
+      trace_alloc_max_entries: 100000
+      stack_depth: 32
+      context: all
+      stacks: all
+      kw_args: {}
+transfer_queue:
+  enable: false
+ray_kwargs:
+  ray_init:
+    num_cpus: 32
+    address: local
+  timeline_json_file: null