williamium commited on
Commit
da773d7
·
verified ·
1 Parent(s): 0ebcc87

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 +1 -0
  2. tt-v4_45_full/global_step_104/data.pt +3 -0
  3. tt-v4_45_full/global_step_112/data.pt +3 -0
  4. tt-v4_45_full/global_step_120/data.pt +3 -0
  5. tt-v4_45_full/global_step_128/data.pt +3 -0
  6. tt-v4_45_full/global_step_136/data.pt +3 -0
  7. tt-v4_45_full/global_step_144/data.pt +3 -0
  8. tt-v4_45_full/global_step_152/data.pt +3 -0
  9. tt-v4_45_full/global_step_16/data.pt +3 -0
  10. tt-v4_45_full/global_step_160/data.pt +3 -0
  11. tt-v4_45_full/global_step_168/data.pt +3 -0
  12. tt-v4_45_full/global_step_176/data.pt +3 -0
  13. tt-v4_45_full/global_step_184/data.pt +3 -0
  14. tt-v4_45_full/global_step_192/data.pt +3 -0
  15. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_0.pt +3 -0
  16. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_1.pt +3 -0
  17. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_2.pt +3 -0
  18. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_3.pt +3 -0
  19. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_4.pt +3 -0
  20. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_5.pt +3 -0
  21. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_6.pt +3 -0
  22. tt-v4_45_full/global_step_199/actor/extra_state_world_size_8_rank_7.pt +3 -0
  23. tt-v4_45_full/global_step_199/actor/fsdp_config.json +4 -0
  24. tt-v4_45_full/global_step_199/actor/huggingface/added_tokens.json +24 -0
  25. tt-v4_45_full/global_step_199/actor/huggingface/chat_template.jinja +10 -0
  26. tt-v4_45_full/global_step_199/actor/huggingface/config.json +140 -0
  27. tt-v4_45_full/global_step_199/actor/huggingface/generation_config.json +12 -0
  28. tt-v4_45_full/global_step_199/actor/huggingface/merges.txt +0 -0
  29. tt-v4_45_full/global_step_199/actor/huggingface/preprocessor_config.json +39 -0
  30. tt-v4_45_full/global_step_199/actor/huggingface/special_tokens_map.json +31 -0
  31. tt-v4_45_full/global_step_199/actor/huggingface/tokenizer.json +3 -0
  32. tt-v4_45_full/global_step_199/actor/huggingface/tokenizer_config.json +208 -0
  33. tt-v4_45_full/global_step_199/actor/huggingface/video_preprocessor_config.json +43 -0
  34. tt-v4_45_full/global_step_199/actor/huggingface/vocab.json +0 -0
  35. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_0.pt +3 -0
  36. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_1.pt +3 -0
  37. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_2.pt +3 -0
  38. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_3.pt +3 -0
  39. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_4.pt +3 -0
  40. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_5.pt +3 -0
  41. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_6.pt +3 -0
  42. tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_7.pt +3 -0
  43. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_0.pt +3 -0
  44. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_1.pt +3 -0
  45. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_2.pt +3 -0
  46. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_3.pt +3 -0
  47. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_4.pt +3 -0
  48. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_5.pt +3 -0
  49. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_6.pt +3 -0
  50. tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_7.pt +3 -0
.gitattributes CHANGED
@@ -19735,3 +19735,4 @@ tt-v3_qwen2.5vl-7b-instruct/global_step_58/actor/huggingface/tokenizer.json filt
19735
  tt-v4.33judge_qwen2.5vl-7b_full/global_step_64/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
19736
  tt-v4_3cov_qwen25vl32b_instruct/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
19737
  tt-v4_3_full_qwen2_5vl_7b_instruct/global_step_199/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
19735
  tt-v4.33judge_qwen2.5vl-7b_full/global_step_64/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
19736
  tt-v4_3cov_qwen25vl32b_instruct/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
19737
  tt-v4_3_full_qwen2_5vl_7b_instruct/global_step_199/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
19738
+ tt-v4_45_full/global_step_199/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tt-v4_45_full/global_step_104/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2489c46d2beea4321af094485ad80715e0885d90eb0c671112989dbcfe6679
3
+ size 7316
tt-v4_45_full/global_step_112/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b4d2856363c4c77d3bd6de01b178f3c1e7dd9501298c329cb90b7e36c94a28
3
+ size 7316
tt-v4_45_full/global_step_120/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a48d9c20fb81048b816db042391c840b51bf9b74567900d5c64394bdbe739e0
3
+ size 7316
tt-v4_45_full/global_step_128/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78f423aadd81ce1d801fd5ef479ca1745e0b399b55f7c3fa46e42c81f622f5f1
3
+ size 7316
tt-v4_45_full/global_step_136/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9045c08d73e1f4f4e8646746fd7f20d07813f8c9727e2bf58130ac75105efe16
3
+ size 7316
tt-v4_45_full/global_step_144/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6656dda127f0be63dd2bf249c70d7796b5c750f96e39ae5c97a4e2d1c425fe7d
3
+ size 7316
tt-v4_45_full/global_step_152/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900360dc0a34bbbc41f725512bdd4056b6ae2e7120e04730a1118b9ed6f6a913
3
+ size 7316
tt-v4_45_full/global_step_16/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d0e4e8d144d42fa234a2f61cc9fcf7be764fe0ebbba11a2694fe5c8ff2d7f3
3
+ size 7316
tt-v4_45_full/global_step_160/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8330a6d289f2e002665c85b6417b477c1fe5143a8aa5949e06a73ca24e54cc0
3
+ size 7316
tt-v4_45_full/global_step_168/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0a92cf88839f48e06273583f4de37dcd27780eb1c7f8e5924b7e078a0e4171
3
+ size 7316
tt-v4_45_full/global_step_176/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a50cca735853453b8f002a0bd85484728ba72f8404fb3c689370def020d130
3
+ size 7316
tt-v4_45_full/global_step_184/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fef99f953bc40866f07aea1f1258b353aeca8d887b598c9ff26087b53fadb5a
3
+ size 7316
tt-v4_45_full/global_step_192/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68df894413607bba4db218904b19a56b934dccb28e9ab6c85bb5f635f8a8fd28
3
+ size 7316
tt-v4_45_full/global_step_199/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:dfa506784b25ce8c6d4354381c55ed2846770c881f972971c69b43092258a727
3
+ size 15141
tt-v4_45_full/global_step_199/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 sha256:50a63dffbd363cb640987140a16cef48649043c51553acae67ed39a098433439
3
+ size 15141
tt-v4_45_full/global_step_199/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 sha256:624a063b69ef236b4c39bde243d680c2c3ad710ad427a10532e1e943dad1b174
3
+ size 15077
tt-v4_45_full/global_step_199/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:e692165984ce542e47ab20b08599e3a8021d132648d27ecdbadf736a63b3e926
3
+ size 15141
tt-v4_45_full/global_step_199/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 sha256:4a4a5a21832e67a22a4986a0ce6fa8acc5ef6e547b4976b3e595536d1d6db7e7
3
+ size 15141
tt-v4_45_full/global_step_199/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 sha256:1076002b6b52a5ebdad7533722e7d8a085f21ccb06b7749b1b60c56b9fec1ba2
3
+ size 15141
tt-v4_45_full/global_step_199/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 sha256:3897bb8ab4ed8cad2e96445200328070e39fd7bafb5dcfe38ebee02b13371e02
3
+ size 15141
tt-v4_45_full/global_step_199/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:ccd04b4c63fb5fac4271a2f6229242839959a67dce58054f18d5da1b6ff1acb1
3
+ size 15141
tt-v4_45_full/global_step_199/actor/fsdp_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "FSDP_version": 1,
3
+ "world_size": 8
4
+ }
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/actor/huggingface/chat_template.jinja ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{%- if tools %}{{- '<|im_start|>system\n' }}{%- if messages[0]['role'] == 'system' %}{%- if messages[0]['content'] is string %}{{- messages[0]['content'] }}{%- else %}{{- messages[0]['content'][0]['text'] }}{%- endif %}{%- else %}{{- 'You are a helpful assistant.' }}{%- endif %}{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}{%- for tool in tools %}{{- "\n" }}{{- tool | tojson }}{%- endfor %}{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}{% for message in messages %}{% if message['role'] != 'system' or loop.first == false %}{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}<|im_start|>{{ message['role'] }}
2
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
3
+ {% 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|>
4
+ {% endif %}{%- elif message.role == "assistant" %}{{- '<|im_start|>' + message.role }}{%- if message.content %}{{- '\n' + message.content }}{%- endif %}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}{{- '\n<tool_call>\n{"name": "' }}{{- tool_call.name }}{{- '", "arguments": ' }}{{- tool_call.arguments | tojson }}{{- '}\n</tool_call>' }}{%- endfor %}{{- '<|im_end|>\n' }}{%- elif message.role == "tool" %}{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}{{- '\n<tool_response>\n' }}{% if message['content'] is string %}{{ message.content }}{% 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 content['type'] == 'text' or 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{- '\n</tool_response>' }}{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}{%- endif %}{% endif %}{% endfor %}{%- else %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
5
+ You are a helpful assistant.<|im_end|>
6
+ {% endif %}{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}<|im_start|>{{ message['role'] }}
7
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
8
+ {% 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|>
9
+ {% endif %}{%- elif message.role == "assistant" %}{{- '<|im_start|>' + message.role }}{%- if message.content %}{{- '\n' + message.content }}{%- endif %}{%- for tool_call in message.tool_calls %}{%- if tool_call.function is defined %}{%- set tool_call = tool_call.function %}{%- endif %}{{- '\n<tool_call>\n{"name": "' }}{{- tool_call.name }}{{- '", "arguments": ' }}{{- tool_call.arguments | tojson }}{{- '}\n</tool_call>' }}{%- endfor %}{{- '<|im_end|>\n' }}{%- elif message.role == "tool" %}{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}{{- '\n<tool_response>\n' }}{% if message['content'] is string %}{{ message.content }}{% 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 content['type'] == 'text' or 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{- '\n</tool_response>' }}{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}{%- endif %}{% endfor %}{%- endif %}{% if add_generation_prompt %}<|im_start|>assistant
10
+ {% endif %}
tt-v4_45_full/global_step_199/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": "/mnt/bn/tns-algo-video-vlm-ruby/yijiangli/project/ckpts/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
+ }
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/actor/huggingface/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/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
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/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
+ }
tt-v4_45_full/global_step_199/actor/huggingface/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c4aa6afeb17effd40b983c2007e84a51ebf5afef882fa611838948cc70ca17
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83bf6ab488ab0f74c2ff50cd4c5c64496975791408f53e62514eca42b68b9586
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4eb94fa4db30d9e898253759411ee5009f99b42418bc0f31f92f2ffa49d292
3
+ size 2033526027
tt-v4_45_full/global_step_199/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:d4cd2744367e023d1132d1800129abebf0cf91414c3845c704fb407edd9f04f0
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892abf1968cb8c60c5ac51b33f156d6c2e7ef87453db30ab02c046eb3e156389
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f87bd9d8a0d7643ac69d28ca81e873550d70c8295f34b46cbbc7ae7ec4af71
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881c56b08b10b863d41377ea148f16cf0b8cab8c466bd5bf9ce2cee96dc44d45
3
+ size 2033526027
tt-v4_45_full/global_step_199/actor/model_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c70b1367e2070c14a7e9415c9fd017fa3ce5d22c2cfe899056dfb84c8ba5b18
3
+ size 2032211211
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec341c7131f55b0523c2dec3bdf00dbb553cd75535dcb1b1be26477912c1f51
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38096ad6b0eb67f00d2d416cb9708b6e9939224a55d22ca0f87ca1023beb84e9
3
+ size 3754803163
tt-v4_45_full/global_step_199/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:babddff5778883d473e9e05c0ff30c22d2ef6be1a0228886e50ae0f7a5272e31
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733f2457dafc55aeb044cd0e60bbd703ea337e1d11f778a2e266178255150318
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468025d9ddf2db999e87fee70c96e3ae2a0939fc505f94032060f2a26662e87a
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3027d7fdd7cad1b6f900113e0e273d5c7cca5566af55ee07e297584e020ff99f
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6026b23fc6d1ccbcde5d89f1deadbcd1f906b67cb311562400bcf0bd98935d
3
+ size 3754803163
tt-v4_45_full/global_step_199/actor/optim_world_size_8_rank_7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab40794503054ed27aa31f0e378157eed0720984474ea4e686fbe600d1fdbb9
3
+ size 3754803163