williamium commited on
Commit
67cc5fa
·
verified ·
1 Parent(s): 9f7f821

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +8 -0
  2. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_0.pt +3 -0
  3. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_1.pt +3 -0
  4. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_2.pt +3 -0
  5. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_3.pt +3 -0
  6. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_4.pt +3 -0
  7. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_5.pt +3 -0
  8. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_6.pt +3 -0
  9. deepeyes/global_step_104/actor/extra_state_world_size_8_rank_7.pt +3 -0
  10. deepeyes/global_step_104/actor/huggingface/added_tokens.json +24 -0
  11. deepeyes/global_step_104/actor/huggingface/chat_template.json +3 -0
  12. deepeyes/global_step_104/actor/huggingface/config.json +66 -0
  13. deepeyes/global_step_104/actor/huggingface/merges.txt +0 -0
  14. deepeyes/global_step_104/actor/huggingface/preprocessor_config.json +29 -0
  15. deepeyes/global_step_104/actor/huggingface/special_tokens_map.json +31 -0
  16. deepeyes/global_step_104/actor/huggingface/tokenizer.json +3 -0
  17. deepeyes/global_step_104/actor/huggingface/tokenizer_config.json +209 -0
  18. deepeyes/global_step_104/actor/huggingface/vocab.json +0 -0
  19. deepeyes/global_step_104/actor/model_world_size_8_rank_0.pt +3 -0
  20. deepeyes/global_step_104/actor/model_world_size_8_rank_1.pt +3 -0
  21. deepeyes/global_step_104/actor/model_world_size_8_rank_2.pt +3 -0
  22. deepeyes/global_step_104/actor/model_world_size_8_rank_3.pt +3 -0
  23. deepeyes/global_step_104/actor/model_world_size_8_rank_4.pt +3 -0
  24. deepeyes/global_step_104/actor/model_world_size_8_rank_5.pt +3 -0
  25. deepeyes/global_step_104/actor/model_world_size_8_rank_6.pt +3 -0
  26. deepeyes/global_step_104/actor/model_world_size_8_rank_7.pt +3 -0
  27. deepeyes/global_step_104/actor/optim_world_size_8_rank_0.pt +3 -0
  28. deepeyes/global_step_104/actor/optim_world_size_8_rank_1.pt +3 -0
  29. deepeyes/global_step_104/actor/optim_world_size_8_rank_2.pt +3 -0
  30. deepeyes/global_step_104/actor/optim_world_size_8_rank_3.pt +3 -0
  31. deepeyes/global_step_104/actor/optim_world_size_8_rank_4.pt +3 -0
  32. deepeyes/global_step_104/actor/optim_world_size_8_rank_5.pt +3 -0
  33. deepeyes/global_step_104/actor/optim_world_size_8_rank_6.pt +3 -0
  34. deepeyes/global_step_104/actor/optim_world_size_8_rank_7.pt +3 -0
  35. deepeyes/global_step_104/data.pt +3 -0
  36. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_0.pt +3 -0
  37. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_1.pt +3 -0
  38. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_2.pt +3 -0
  39. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_3.pt +3 -0
  40. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_4.pt +3 -0
  41. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_5.pt +3 -0
  42. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_6.pt +3 -0
  43. deepeyes/global_step_112/actor/extra_state_world_size_8_rank_7.pt +3 -0
  44. deepeyes/global_step_112/actor/huggingface/added_tokens.json +24 -0
  45. deepeyes/global_step_112/actor/huggingface/chat_template.json +3 -0
  46. deepeyes/global_step_112/actor/huggingface/config.json +66 -0
  47. deepeyes/global_step_112/actor/huggingface/merges.txt +0 -0
  48. deepeyes/global_step_112/actor/huggingface/preprocessor_config.json +29 -0
  49. deepeyes/global_step_112/actor/huggingface/special_tokens_map.json +31 -0
  50. deepeyes/global_step_112/actor/huggingface/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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
+ deepeyes/global_step_104/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ deepeyes/global_step_112/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ deepeyes/global_step_16/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ deepeyes/global_step_32/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ deepeyes/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ deepeyes/global_step_64/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ deepeyes/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ deepeyes/global_step_96/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68cdc8b2b9c1e353228d0938bdf5b3d9aca9a581b1b7ff1a7b281d91e062a5a
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5585299aef978b16c22b641eb90c57b69270043063bb6b6d0ef5b8001665a3dc
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df4023707e91f8548d8079856b5dc73b5ea8246f1ca2b39d919b83b0337e461
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8beb8b609f0dc3192d43a71446ff29ac0b5ee8de792f965c006dd64600785d2
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571103df68ce4a3fb5ce22819d93905ea962a760aa44b8f2058b4aa6949489b1
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626a98e86ac59a85820028b82c346ee0f2cb45f98ed0d876620049f3d4af3b10
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b706bf38b04726d5d13b0effd932965d53a8b527a7cb81d5ae25d0fd8b56c996
3
+ size 15077
deepeyes/global_step_104/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21252d51c6b5b20c812073b876c7dca5603de71d73bdcbcac4e3727b0f3f38eb
3
+ size 15077
deepeyes/global_step_104/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
+ }
deepeyes/global_step_104/actor/huggingface/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
deepeyes/global_step_104/actor/huggingface/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
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
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.51.3",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "depth": 32,
40
+ "fullatt_block_indexes": [
41
+ 7,
42
+ 15,
43
+ 23,
44
+ 31
45
+ ],
46
+ "hidden_act": "silu",
47
+ "hidden_size": 1280,
48
+ "in_channels": 3,
49
+ "in_chans": 3,
50
+ "intermediate_size": 3420,
51
+ "model_type": "qwen2_5_vl",
52
+ "num_heads": 16,
53
+ "out_hidden_size": 3584,
54
+ "patch_size": 14,
55
+ "spatial_merge_size": 2,
56
+ "spatial_patch_size": 14,
57
+ "temporal_patch_size": 2,
58
+ "tokens_per_second": 2,
59
+ "torch_dtype": "float32",
60
+ "window_size": 112
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vision_token_id": 151654,
65
+ "vocab_size": 152064
66
+ }
deepeyes/global_step_104/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
deepeyes/global_step_104/actor/huggingface/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
deepeyes/global_step_104/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
+ }
deepeyes/global_step_104/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
deepeyes/global_step_104/actor/huggingface/tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
deepeyes/global_step_104/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
deepeyes/global_step_104/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d7923613f00db34f81112df59a5daa0ed731a55ff07a006331658dcdad3220
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc7326dac92b3a06c8c15c4a4c4d5346344c0ff38e08292f9e81be661f59081
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4ba4da939fce563f38ac7eddd76f4d29afeae868f77ba5a1f6eb08c666bc7a
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b2e17a322f10fb1a1c351b7f8c5d226fb81373660891deeb2c243f43bf097e
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a067c3f4bb2ae6eac329bcdedacd68abb7f45b160d8db191f2b4f61bc1de87
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7503e01f68a1ee4e7f3ad89efa9be3dbff4613447587b0076e8392772591c53c
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b067a87f670d679537d4b95609a0c702d0f9439ecc98fd96e7e6e9b3b9e5e9
3
+ size 4146642571
deepeyes/global_step_104/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176153dfd2391db9da5e597bb1acd329caf96a391f052b2452f3e8bd4922c998
3
+ size 4145327755
deepeyes/global_step_104/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b92286b0a54b9354ff20c1cfdb1d3595bbc3f3dfcb7ac28f9fee90ef7f3931f
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd6b353f8afd757b7149374c13fb7a85999fdd317d2d5e936c307fbf0a89ac7
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711b5d9f5e7b787b5cd254888f9e96c2d4d394ee296a695745489fa6b85e33d6
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb78c12406fa8a6bd164c6f56f38a3a9e53f76e93c97719b2b989fe707d42fe
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7b420905be3f825b18874d7a2b9300f87950c81a3e0c1e7e0a985fa4d469d8
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3306ddf41f2f476c6fbd8d5827e4faaf839750bc49357870f138399206d72eb
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a04681b7b39e68f03192f3f3d466c8f8f29cadc00aa608607e126194b1443b
3
+ size 8292218719
deepeyes/global_step_104/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cbe154e1393946f730fcfdac0e88a76dc7af2daf608f177aea109ab64980d88
3
+ size 8292218719
deepeyes/global_step_104/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4861d7ecdae7735f1af454df0c89227c7e74a4c1ba7a76f27cddf3448cff1f90
3
+ size 1947
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97942253138018ebb9c44742c5fb410cd77400e8494e6a45da285bd42b62e57b
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928fab54ec7da8babfc0af539d143204416922222eb0d7c5058f234a9252221
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43106e70548ea9f2515517573ae6aa5843adada5e2a9498ea0b154ec38cc6385
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d375256634e89db525a263f3435005c3ecbc746c0d26318cefd669fc1f077df
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f98efee89b223e79c835fe8d790f7a2f573e4e05440e5e63bd98157e70e1f5
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ca031d5b63e0a54d6cbf1d5d0abbb487e3ced55f96745bf8f8f1f0e911c733
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ec04f2576c6a3d4fdd49346101cd571fe6f8e4ec82836939b16ab91998c2dd
3
+ size 15077
deepeyes/global_step_112/actor/extra_state_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce183104137a286c573b04b6fb6114dadeafba340e56496849a7975d383ac94
3
+ size 15077
deepeyes/global_step_112/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
+ }
deepeyes/global_step_112/actor/huggingface/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
deepeyes/global_step_112/actor/huggingface/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 151643,
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
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.51.3",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "depth": 32,
40
+ "fullatt_block_indexes": [
41
+ 7,
42
+ 15,
43
+ 23,
44
+ 31
45
+ ],
46
+ "hidden_act": "silu",
47
+ "hidden_size": 1280,
48
+ "in_channels": 3,
49
+ "in_chans": 3,
50
+ "intermediate_size": 3420,
51
+ "model_type": "qwen2_5_vl",
52
+ "num_heads": 16,
53
+ "out_hidden_size": 3584,
54
+ "patch_size": 14,
55
+ "spatial_merge_size": 2,
56
+ "spatial_patch_size": 14,
57
+ "temporal_patch_size": 2,
58
+ "tokens_per_second": 2,
59
+ "torch_dtype": "float32",
60
+ "window_size": 112
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vision_token_id": 151654,
65
+ "vocab_size": 152064
66
+ }
deepeyes/global_step_112/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
deepeyes/global_step_112/actor/huggingface/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
deepeyes/global_step_112/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
+ }
deepeyes/global_step_112/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