Silin1590 commited on
Commit
ee70251
·
verified ·
1 Parent(s): 253c537

Add files using upload-large-folder tool

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. checkpoints/ablation/no_dropout/model.safetensors +3 -0
  3. checkpoints/ablation/no_reweight/ema.safetensors +3 -0
  4. checkpoints/ablation/no_vwm_attn/ema.safetensors +3 -0
  5. checkpoints/ablation/origin/ema.safetensors +3 -0
  6. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000050/scheduler.pt +3 -0
  7. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/data_status.pt +3 -0
  8. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/model.safetensors +3 -0
  9. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/scheduler.pt +3 -0
  10. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/added_tokens.json +24 -0
  11. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/chat_template.jinja +54 -0
  12. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/config.json +62 -0
  13. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/data_status.pt +3 -0
  14. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/llm_config.json +27 -0
  15. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/merges.txt +0 -0
  16. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/model.safetensors.index.json +0 -0
  17. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/special_tokens_map.json +31 -0
  18. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/tokenizer.json +3 -0
  19. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/tokenizer_config.json +207 -0
  20. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/vit_config.json +9 -0
  21. checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/vocab.json +0 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  vwp_stb_data/vwp_train_fwd_vwm.jsonl 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
  vwp_stb_data/vwp_train_fwd_vwm.jsonl filter=lfs diff=lfs merge=lfs -text
37
+ checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/ablation/no_dropout/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c139484fd5628ed3116afef55ed0b8b0873601084b2b75209f0b77677fc45543
3
+ size 58429204680
checkpoints/ablation/no_reweight/ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444451ceed33b3a53fd86eedb1ca453fbe6dfdf11f1aa2ddf90ea7e1774baf04
3
+ size 58429204680
checkpoints/ablation/no_vwm_attn/ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7f84aa0e8369e1499be46dbcd09f6ed193bc47385df367dbd16b4f626f12ec
3
+ size 58429204680
checkpoints/ablation/origin/ema.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae61875bf557da8705f7015b49de05461a7a99ef75370589c9f90bc1fe6531e2
3
+ size 58429204680
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000050/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159c6c87d55a25f61a5a55935036ae924b0e166826a8b76c1bf1f9c8e6650db6
3
+ size 1401
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/data_status.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2e22a4b86bd88e862f78c4084af5888ae129e2f57c6555c5311f8df7fda3ab
3
+ size 1733
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a03bb50e4c71b0449413cd5e18577cacc664139633512879f765e7df2923843
3
+ size 58313555040
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f7bf1ab30711069f88517a7b739751489ab89a16971697b7bc17899d5bb5ba
3
+ size 1401
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/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
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BagelForConditionalGeneration"
4
+ ],
5
+ "model_type": "bagel",
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_bagel.BagelConfig",
8
+ "AutoModelForCausalLM": "modeling_bagel.BagelForConditionalGeneration"
9
+ },
10
+ "visual_gen": true,
11
+ "visual_und": true,
12
+ "llm_config": {
13
+ "architectures": [
14
+ "Qwen2ForCausalLM"
15
+ ],
16
+ "attention_dropout": 0.0,
17
+ "bos_token_id": 151643,
18
+ "eos_token_id": 151645,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 3584,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 18944,
23
+ "max_position_embeddings": 32768,
24
+ "max_window_layers": 28,
25
+ "model_type": "qwen2",
26
+ "num_attention_heads": 28,
27
+ "num_hidden_layers": 28,
28
+ "num_key_value_heads": 4,
29
+ "qk_norm": true,
30
+ "rms_norm_eps": 1e-06,
31
+ "rope_theta": 1000000.0,
32
+ "sliding_window": 131072,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.43.1",
36
+ "use_cache": true,
37
+ "use_sliding_window": false,
38
+ "vocab_size": 152064
39
+ },
40
+ "vit_config": {
41
+ "hidden_size": 1152,
42
+ "image_size": 980,
43
+ "intermediate_size": 4304,
44
+ "model_type": "siglip_vision_model",
45
+ "num_attention_heads": 16,
46
+ "num_hidden_layers": 27,
47
+ "patch_size": 14,
48
+ "num_channels": 3
49
+ },
50
+ "vae_config": {
51
+ "z_channels": 16,
52
+ "downsample": 8
53
+ },
54
+ "latent_patch_size": 2,
55
+ "max_latent_size": 32,
56
+ "vit_max_num_patch_per_side": 70,
57
+ "connector_act": "gelu_pytorch_tanh",
58
+ "interpolate_pos": false,
59
+ "timestep_shift": 1.0,
60
+ "torch_dtype": "bfloat16",
61
+ "transformers_version": "4.49.0"
62
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/data_status.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fcac37dbed00998e163d8534dc7d61e9fb04ecc5742739fad8ba7d4f02ced5a
3
+ size 1733
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/llm_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.43.1",
24
+ "use_cache": true,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064
27
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/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
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/vit_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hidden_size": 1152,
3
+ "image_size": 980,
4
+ "intermediate_size": 4304,
5
+ "model_type": "siglip_vision_model",
6
+ "num_attention_heads": 16,
7
+ "num_hidden_layers": 27,
8
+ "patch_size": 14
9
+ }
checkpoints/pt_st_mwd6_ol3_full_attn_vlm/baseline_vlm_sft_video_qa_v2/0000150/vocab.json ADDED
The diff for this file is too large to render. See raw diff