Delete all files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/added_tokens.json +0 -24
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/chat_template.jinja +0 -7
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/config.json +0 -140
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/generation_config.json +0 -12
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/merges.txt +0 -0
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/preprocessor_config.json +0 -39
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/special_tokens_map.json +0 -31
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/tokenizer.json +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/tokenizer_config.json +0 -208
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/video_preprocessor_config.json +0 -43
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/vocab.json +0 -0
- geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/data.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/added_tokens.json +0 -24
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/chat_template.jinja +0 -7
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/config.json +0 -140
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/generation_config.json +0 -12
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/merges.txt +0 -0
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_0.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_1.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_2.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_3.pt +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/preprocessor_config.json +0 -39
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/special_tokens_map.json +0 -31
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/tokenizer.json +0 -3
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/tokenizer_config.json +0 -208
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/video_preprocessor_config.json +0 -43
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/vocab.json +0 -0
- geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/data.pt +0 -3
- geo3k_2509_Qwen2.5-VL-7B-Instruct_grpo/actor/added_tokens.json +0 -24
- geo3k_2509_Qwen2.5-VL-7B-Instruct_grpo/actor/chat_template.jinja +0 -7
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/added_tokens.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/chat_template.jinja
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/config.json
DELETED
|
@@ -1,140 +0,0 @@
|
|
| 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": "4.57.0",
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:766a1cebb346f9c9433166fef12b6868a22e629b80c588eb4187c34acada72dc
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:48b5c7b90ce0f4a509dfc562300603255eeef992804cc0d4475b3cf433b88273
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f194f73b1d29812dad2b4c402899e3f82dcf27ddbed830184db0741b4cf5cf4f
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/extra_state_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2e1b9969d25b8a5896e23f86fd28b29293983366563f34c1f4baa68eb24bd27f
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 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": "4.57.0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b03b908113b4b3d502666fefc9aa4d705482270ec587b0e8608fd6da8f411562
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b72f4f59f05763d9dec7c3aa78c4040fede5909e1d8344ef13e38141cc908ba2
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:246b96dea0331096f2a17e50b44a4f6284c42e4a9ab0e52ddac6bd0a2a94fe06
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/model_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b6b19dd0e5546ce83c1ac2e8c88ba7e274808e9c32814be06dc978dda55a1a5c
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e3296916373642eac4472fdc27917adffd6bf8dc11fe02f13d06a8f0d084edb1
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d02397750d22a56aeaa0a2355de9a84047ed106aa55697046a02c3f265c8bd3a
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3800908071e9fa072b9e426990e95a3d1c1681f179bcb837222c31abb6f3a605
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/optim_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:160419b97117a584a9628046878092f2463a97b74f849d80f818497c5b1661a8
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/preprocessor_config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
-
size 11421896
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/tokenizer_config.json
DELETED
|
@@ -1,208 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/video_preprocessor_config.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/actor/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_grpo/data.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6bbb46d0717d2cb84f16f19b375f8d23ef4412a401e6af1cac1e8ed19d7d38c9
|
| 3 |
-
size 1947
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/added_tokens.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/chat_template.jinja
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/config.json
DELETED
|
@@ -1,140 +0,0 @@
|
|
| 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": "4.57.0",
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cccf548cb7ea17a8148eee53cf2c87dc0b03de2335ee4eb4b8cc43d970b4a383
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:495adc68d1094b0516825e25fa50fbe5516dde052c51b8360c9d0cabf0673b47
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9e715576ae559000e6040f94e9cc61e4772618dc4b508b88aa25630be6ffe503
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/extra_state_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:028640f5cbb38b06bd0fdac9e4a03a058392d5cbb696574643906ef00adedb97
|
| 3 |
-
size 15077
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 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": "4.57.0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:943a5412f6b4731a5488251bfa716df8764c1fcd48daba47c733e1c183106d26
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a55bf638625da1b890d72e6251dd94f41bdcf554b55e8f7b15ee10e2c24479e2
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:4acbfad6c338a9fce3a18a9abe642501010adc030e307f73578c74fdbcaeb3e5
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/model_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6df0aff641e7d6b30062b34552f9fa75f38c5c0a7b8225ecafea1f8922b1c900
|
| 3 |
-
size 4066253515
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_0.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:35d05e1bb30a3d33733c714184dd5a1b345064dd80b74ea2c1bc3149a0f7f60c
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_1.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:35c74140a13c07f264f90c2eef9d9521585081080018727889c7b672b6b40822
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_2.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6388765c9570fe8f229123dd824444f1857fb4d6015be41e502905677ebb5bf5
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/optim_world_size_4_rank_3.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:decbe7750a1e15e788c9caf9290361d81c16a933964c77097069e9043625cc6e
|
| 3 |
-
size 7509307287
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/preprocessor_config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
-
size 11421896
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/tokenizer_config.json
DELETED
|
@@ -1,208 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/video_preprocessor_config.json
DELETED
|
@@ -1,43 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/actor/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
geo3k_2509_Qwen2.5-VL-3B-Instruct_lbr_grpo/data.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:fc57588c0e74dfe41a6a33b9ab1b3492c8b63427244942503cd661831c44b597
|
| 3 |
-
size 1947
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-7B-Instruct_grpo/actor/added_tokens.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
geo3k_2509_Qwen2.5-VL-7B-Instruct_grpo/actor/chat_template.jinja
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|