Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_0.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_1.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_2.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_3.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_4.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_5.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/fsdp_config.json +4 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/added_tokens.json +24 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/chat_template.jinja +7 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/config.json +140 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/generation_config.json +12 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/merges.txt +0 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/preprocessor_config.json +39 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/special_tokens_map.json +31 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer.json +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer_config.json +208 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/video_preprocessor_config.json +43 -0
- llava_vqa_judge_grpo_local_qwen3/actor/huggingface/vocab.json +0 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_0.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_1.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_2.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_3.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_4.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_5.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_0.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_1.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_2.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_3.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_4.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_5.pt +3 -0
- llava_vqa_judge_grpo_local_qwen3/data.pt +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:086ec002f19c12f678d2b0be1c004e182a6bed723017f1686b9e4effa6ce9093
|
| 3 |
+
size 15205
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12e3c49f963b1fd9702230a78f033f2a1caf756d9b92a920fd16690311748862
|
| 3 |
+
size 15141
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5808a2cbd9daa41493271d9c6e2832be7580fc7c3cf174af56c3805c51ea23f5
|
| 3 |
+
size 15141
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61fe1de5a7ed273a7a3ceb9124b043ec458dcba6afede8077a414c2e780bc376
|
| 3 |
+
size 15141
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08f80bb823c4ee051b9bef12662d8193ef766ef7e94435fac7e56600756a2d93
|
| 3 |
+
size 15141
|
llava_vqa_judge_grpo_local_qwen3/actor/extra_state_world_size_6_rank_5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29d461bf8589e325f460ef3d98cc1ce3f0f55431ee4e504370fadc216a5a9a21
|
| 3 |
+
size 15141
|
llava_vqa_judge_grpo_local_qwen3/actor/fsdp_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"FSDP_version": 1,
|
| 3 |
+
"world_size": 6
|
| 4 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% 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
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% 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|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/config.json
ADDED
|
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 70,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 36,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": {
|
| 22 |
+
"mrope_section": [
|
| 23 |
+
16,
|
| 24 |
+
24,
|
| 25 |
+
24
|
| 26 |
+
],
|
| 27 |
+
"rope_type": "default",
|
| 28 |
+
"type": "default"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 1000000.0,
|
| 31 |
+
"sliding_window": 32768,
|
| 32 |
+
"text_config": {
|
| 33 |
+
"_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
|
| 34 |
+
"architectures": [
|
| 35 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 36 |
+
],
|
| 37 |
+
"attention_dropout": 0.0,
|
| 38 |
+
"dtype": "float32",
|
| 39 |
+
"eos_token_id": 151645,
|
| 40 |
+
"hidden_act": "silu",
|
| 41 |
+
"hidden_size": 2048,
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 11008,
|
| 44 |
+
"layer_types": [
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention",
|
| 80 |
+
"full_attention"
|
| 81 |
+
],
|
| 82 |
+
"max_position_embeddings": 128000,
|
| 83 |
+
"max_window_layers": 70,
|
| 84 |
+
"model_type": "qwen2_5_vl_text",
|
| 85 |
+
"num_attention_heads": 16,
|
| 86 |
+
"num_hidden_layers": 36,
|
| 87 |
+
"num_key_value_heads": 2,
|
| 88 |
+
"pad_token_id": 151643,
|
| 89 |
+
"rms_norm_eps": 1e-06,
|
| 90 |
+
"rope_scaling": {
|
| 91 |
+
"mrope_section": [
|
| 92 |
+
16,
|
| 93 |
+
24,
|
| 94 |
+
24
|
| 95 |
+
],
|
| 96 |
+
"rope_type": "default",
|
| 97 |
+
"type": "default"
|
| 98 |
+
},
|
| 99 |
+
"rope_theta": 1000000.0,
|
| 100 |
+
"sliding_window": null,
|
| 101 |
+
"tie_word_embeddings": true,
|
| 102 |
+
"use_cache": true,
|
| 103 |
+
"use_sliding_window": false,
|
| 104 |
+
"vision_token_id": 151654,
|
| 105 |
+
"vocab_size": 151936
|
| 106 |
+
},
|
| 107 |
+
"transformers_version": "4.57.1",
|
| 108 |
+
"use_cache": true,
|
| 109 |
+
"use_sliding_window": false,
|
| 110 |
+
"video_token_id": 151656,
|
| 111 |
+
"vision_config": {
|
| 112 |
+
"depth": 32,
|
| 113 |
+
"dtype": "float32",
|
| 114 |
+
"fullatt_block_indexes": [
|
| 115 |
+
7,
|
| 116 |
+
15,
|
| 117 |
+
23,
|
| 118 |
+
31
|
| 119 |
+
],
|
| 120 |
+
"hidden_act": "silu",
|
| 121 |
+
"hidden_size": 1280,
|
| 122 |
+
"in_channels": 3,
|
| 123 |
+
"in_chans": 3,
|
| 124 |
+
"initializer_range": 0.02,
|
| 125 |
+
"intermediate_size": 3420,
|
| 126 |
+
"model_type": "qwen2_5_vl",
|
| 127 |
+
"num_heads": 16,
|
| 128 |
+
"out_hidden_size": 2048,
|
| 129 |
+
"patch_size": 14,
|
| 130 |
+
"spatial_merge_size": 2,
|
| 131 |
+
"spatial_patch_size": 14,
|
| 132 |
+
"temporal_patch_size": 2,
|
| 133 |
+
"tokens_per_second": 2,
|
| 134 |
+
"window_size": 112
|
| 135 |
+
},
|
| 136 |
+
"vision_end_token_id": 151653,
|
| 137 |
+
"vision_start_token_id": 151652,
|
| 138 |
+
"vision_token_id": 151654,
|
| 139 |
+
"vocab_size": 151936
|
| 140 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "4.57.1"
|
| 12 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.48145466,
|
| 15 |
+
0.4578275,
|
| 16 |
+
0.40821073
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.26862954,
|
| 21 |
+
0.26130258,
|
| 22 |
+
0.27577711
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": 12845056,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": 3136,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 14,
|
| 30 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 12845056,
|
| 36 |
+
"shortest_edge": 3136
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": false,
|
| 12 |
+
"fps": null,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.48145466,
|
| 15 |
+
0.4578275,
|
| 16 |
+
0.40821073
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.26862954,
|
| 20 |
+
0.26130258,
|
| 21 |
+
0.27577711
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"max_pixels": 12845056,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_frames": 4,
|
| 28 |
+
"min_pixels": 3136,
|
| 29 |
+
"num_frames": null,
|
| 30 |
+
"pad_size": null,
|
| 31 |
+
"patch_size": 14,
|
| 32 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 33 |
+
"resample": 3,
|
| 34 |
+
"rescale_factor": 0.00392156862745098,
|
| 35 |
+
"return_metadata": false,
|
| 36 |
+
"size": {
|
| 37 |
+
"longest_edge": 12845056,
|
| 38 |
+
"shortest_edge": 3136
|
| 39 |
+
},
|
| 40 |
+
"temporal_patch_size": 2,
|
| 41 |
+
"video_metadata": null,
|
| 42 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 43 |
+
}
|
llava_vqa_judge_grpo_local_qwen3/actor/huggingface/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76254b72ab2557b624ba20d1353289106817c8cb6583c11206777f1aab0ca0e1
|
| 3 |
+
size 2713260747
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7730b39c7bc915c5d37eba3cd10c8e3627bee0110be0fab2f200f9441c469a7
|
| 3 |
+
size 2713260747
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72c589fd569d842024c238807b8cd3666136f550c0b26b1626930f38261a0eb9
|
| 3 |
+
size 2713260747
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d36a847de0ebd416bca694cee034eeda33b0f6e737836404b81cc8f1968115
|
| 3 |
+
size 2713260747
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f93e4f86d233b1b8a99ed10005d968436ff4fb955e997ec9fb5a32784ec14937
|
| 3 |
+
size 2713260747
|
llava_vqa_judge_grpo_local_qwen3/actor/model_world_size_6_rank_5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f2d9cd86e6b7cc40f8beb3590231532367576d591b5da63c8e68d07ef8d6f83
|
| 3 |
+
size 2699579723
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_0.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:753f3858734a0de27014749969b2e2a60cb331d5cfd25cd266b157c6056e199a
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_1.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ebc7d83964124f65608f042ee28894f1897dcbc1c5524c1682e3273db9a5530
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_2.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a649173856ccd4b1afa292ebabd8daa50a49420ffeb5ffaf0547ca4d78c063
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_3.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8175995551d83a090c30bdf2ae76ea07a91ec0857f99e81d44020f5547a738
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_4.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:254e55b63dd60b0402def957274c39de8088ff379c0d3516c79b9331637cfa3b
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/actor/optim_world_size_6_rank_5.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78cff047bfae600fb7874bf45a6e17150611cc786b4f14c33060ba8464721cb0
|
| 3 |
+
size 5006335391
|
llava_vqa_judge_grpo_local_qwen3/data.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80b1fc344ca03d8350348916a0967a02cd17bd3c5f2a2cc02f3415e6516d4032
|
| 3 |
+
size 7316
|