Hugging Face's logo

YccHugAi
/
lingbot-vla-2-stackcube-ablations

Robotics
Transformers
Safetensors
LeRobot
vla
lingbot-vla
manipulation
Model card Files
xet
 Community
YccHugAi commited on
Commit
4c85611
·
verified ·
1 Parent(s): bf856ff

Add eef100/global_step_5000 (deployable hf_ckpt)

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. eef100/global_step_5000/added_tokens.json +28 -0
  3. eef100/global_step_5000/chat_template.jinja +120 -0
  4. eef100/global_step_5000/config.json +173 -0
  5. eef100/global_step_5000/merges.txt +0 -0
  6. eef100/global_step_5000/model-00001-of-00006.safetensors +3 -0
  7. eef100/global_step_5000/model-00002-of-00006.safetensors +3 -0
  8. eef100/global_step_5000/model-00003-of-00006.safetensors +3 -0
  9. eef100/global_step_5000/model-00004-of-00006.safetensors +3 -0
  10. eef100/global_step_5000/model-00005-of-00006.safetensors +3 -0
  11. eef100/global_step_5000/model-00006-of-00006.safetensors +3 -0
  12. eef100/global_step_5000/model.safetensors.index.json +0 -0
  13. eef100/global_step_5000/preprocessor_config.json +39 -0
  14. eef100/global_step_5000/special_tokens_map.json +31 -0
  15. eef100/global_step_5000/tokenizer.json +3 -0
  16. eef100/global_step_5000/tokenizer_config.json +241 -0
  17. eef100/global_step_5000/video_preprocessor_config.json +41 -0
  18. eef100/global_step_5000/vocab.json +0 -0
.gitattributes CHANGED
@@ -41,3 +41,4 @@ eef/global_step_5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  eef/global_step_10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  eef/global_step_15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  eef/global_step_20000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
41
  eef/global_step_10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  eef/global_step_15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  eef/global_step_20000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ eef100/global_step_5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
eef100/global_step_5000/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
eef100/global_step_5000/chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# 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>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\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" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
eef100/global_step_5000/config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_moe_implementation": "fused",
3
+ "action_dim": 55,
4
+ "action_fp32": false,
5
+ "action_head_dim": 128,
6
+ "action_num_attention_heads": 32,
7
+ "action_num_key_value_heads": 8,
8
+ "adanorm_time": true,
9
+ "align_params": {
10
+ "depth": {
11
+ "block_future_depth_to_action": true,
12
+ "detach_future_image_feats": true,
13
+ "dim_head": 32,
14
+ "dim_out": 1024,
15
+ "ff_mult": 1,
16
+ "input_size": 224,
17
+ "model_type": "MoRGBD",
18
+ "moge_path": "/scratch/cy65664/workDir/lingbot-vla-v2/pretrained/moge-2-vitb-normal/model.pt",
19
+ "morgbd_path": "/scratch/cy65664/workDir/lingbot-vla-v2/pretrained/lingbot-vla-v2-6b/depth/model.pt",
20
+ "num_backbone_tokens": 256,
21
+ "num_heads": 4,
22
+ "num_layers": 1,
23
+ "token_size": 16,
24
+ "use_future_depth": true
25
+ },
26
+ "depth_loss_weight": 0.004,
27
+ "future_depth_loss_weight": 0.004,
28
+ "llm": {
29
+ "dim_out": 2560,
30
+ "image_input_size": 224,
31
+ "image_token_size": 8
32
+ },
33
+ "mode": "query",
34
+ "num_task_tokens": 8,
35
+ "use_future_video": true,
36
+ "video": {
37
+ "attention_mode": "flex_block_causal",
38
+ "block_suffix_to_future_video": true,
39
+ "ckpt_path": "/scratch/cy65664/workDir/lingbot-vla-v2/pretrained/lingbot-vla-v2-6b/dino_video/teacher_step_10000.pth",
40
+ "cls_loss_type": "mse",
41
+ "cls_loss_weight": 0.2,
42
+ "cls_pool": "last",
43
+ "config_path": "/scratch/cy65664/workDir/lingbot-vla-v2/pretrained/lingbot-vla-v2-6b/dino_video/config.yaml",
44
+ "cosine_loss_weight": 0.2,
45
+ "detach_image_feats": true,
46
+ "dim_head": 32,
47
+ "dim_out": 1024,
48
+ "effective_fps": 1.0,
49
+ "ff_mult": 1,
50
+ "future_video_loss_weight": 0.004,
51
+ "input_size": 256,
52
+ "log_max_samples": 32,
53
+ "log_scale": 16,
54
+ "mse_loss_weight": 1.0,
55
+ "n_blocks": 1,
56
+ "num_backbone_tokens": 256,
57
+ "num_future_frames": 1,
58
+ "num_heads": 4,
59
+ "num_layers": 1,
60
+ "share_future_depth_query": true,
61
+ "use_cls_loss": false,
62
+ "use_cosine_loss": false,
63
+ "use_current_patch_loss": true,
64
+ "use_current_shared_task_proj": true,
65
+ "use_mse_loss": true,
66
+ "use_patch_loss": true,
67
+ "use_shared_future_task_proj": true,
68
+ "use_smooth_l1_loss": false,
69
+ "use_warmup_frame": true
70
+ },
71
+ "visual_dir": "output/stackcubes_eef100/images",
72
+ "visual_steps": 5000
73
+ },
74
+ "architectures": [
75
+ "LingbotVlaV2Policy"
76
+ ],
77
+ "attention_implementation": "flex_cached",
78
+ "bias_update_speed": 0.0,
79
+ "chunk_size": 50,
80
+ "depth_incremental_training": false,
81
+ "enable_expert_vision": false,
82
+ "expert_hidden_size": 768,
83
+ "expert_intermediate_size": 2752,
84
+ "expert_vision_path": null,
85
+ "expert_vision_type": null,
86
+ "final_norm_adanorm": false,
87
+ "freeze_vision_encoder": true,
88
+ "incremental_training": false,
89
+ "initializer_range": 0.02,
90
+ "loss_type": "L1_fm",
91
+ "max_action_dim": 55,
92
+ "max_state_dim": 55,
93
+ "model_type": "lingbotvla",
94
+ "moe_implementation": "fused",
95
+ "n_action_steps": 50,
96
+ "n_obs_steps": 1,
97
+ "norm_qkv": false,
98
+ "nosplit_gate_liner": false,
99
+ "num_steps": 10,
100
+ "post_training": true,
101
+ "precompute_grid_thw": true,
102
+ "proj_width": 768,
103
+ "qwen3vl_use_vision_boundaries": true,
104
+ "reinit_mismatched_weights": false,
105
+ "return_image_grid_thw": true,
106
+ "routed_scaling_factor": 4.0,
107
+ "router_activation": "sigmoid",
108
+ "router_z_loss_coeff": 0.0001,
109
+ "separate_time_proj": false,
110
+ "sequence_wise_loss_coeff": 0.001,
111
+ "sequence_wise_mode": "per_sequence",
112
+ "split_fused_experts_from_decoder_fsdp": false,
113
+ "split_gate_liner": false,
114
+ "token_moe_intermediate_size": 512,
115
+ "token_moe_layers": [
116
+ 0,
117
+ 1,
118
+ 2,
119
+ 3,
120
+ 4,
121
+ 5,
122
+ 6,
123
+ 7,
124
+ 8,
125
+ 9,
126
+ 10,
127
+ 11,
128
+ 12,
129
+ 13,
130
+ 14,
131
+ 15,
132
+ 16,
133
+ 17,
134
+ 18,
135
+ 19,
136
+ 20,
137
+ 21,
138
+ 22,
139
+ 23,
140
+ 24,
141
+ 25,
142
+ 26,
143
+ 27,
144
+ 28,
145
+ 29,
146
+ 30,
147
+ 31,
148
+ 32,
149
+ 33,
150
+ 34,
151
+ 35
152
+ ],
153
+ "token_num_experts": 32,
154
+ "token_shared_intermediate_size": 704,
155
+ "token_top_k": 4,
156
+ "tokenizer_max_length": 72,
157
+ "tokenizer_path": "/scratch/cy65664/workDir/lingbot-vla-v2/pretrained/Qwen3-VL-4B-Instruct",
158
+ "train_expert_only": false,
159
+ "train_state_proj": true,
160
+ "transformers_version": "4.57.3",
161
+ "use_cache": false,
162
+ "use_compile": true,
163
+ "use_lm_head": false,
164
+ "use_moe": true,
165
+ "use_qwen3_chat_template": true,
166
+ "use_qwen3_fixed_grid_cache": true,
167
+ "use_shared_expert_gate": false,
168
+ "vit_attn_implementation": "flash_attention_2",
169
+ "vlm_causal": true,
170
+ "vlm_family": "qwen3_vl",
171
+ "vlm_repo_id": null,
172
+ "vocab_size": 257152
173
+ }
eef100/global_step_5000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
eef100/global_step_5000/model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5757caf1777d7875c2f463517173b885dc07aad97c165af24f3a7d07de458d
3
+ size 4947507248
eef100/global_step_5000/model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a798c746d1d303f2efd2843081c1e6448f6addd9e02a0468fa5c5bdcb43bf9e
3
+ size 4944315304
eef100/global_step_5000/model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b031c7fa97c9e259b74fda7c7dd3c45d96c971ae7a4d6e0a2b241ceaf5e9ab
3
+ size 4944315360
eef100/global_step_5000/model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:877de6779861be33c9482ef3548d7c1a3d696a25b108729f03c050b690b480ec
3
+ size 4992858968
eef100/global_step_5000/model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae863dffabbb4dd3ecbebdec789439fb3c4be937392150b7776e410724784afa
3
+ size 4963062048
eef100/global_step_5000/model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494103880101ad7d417aa225e1149c9b28fb716f75019a9773376ca05f01c21a
3
+ size 711830844
eef100/global_step_5000/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
eef100/global_step_5000/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
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": null,
26
+ "merge_size": 2,
27
+ "min_pixels": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 16777216,
36
+ "shortest_edge": 65536
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
eef100/global_step_5000/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
+ }
eef100/global_step_5000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
eef100/global_step_5000/tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "padding_side": "right",
237
+ "processor_class": "Qwen3VLProcessor",
238
+ "split_special_tokens": false,
239
+ "tokenizer_class": "Qwen2Tokenizer",
240
+ "unk_token": null
241
+ }
eef100/global_step_5000/video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
eef100/global_step_5000/vocab.json ADDED
The diff for this file is too large to render. See raw diff