SeaWolf-AI commited on
Commit
057fbce
·
verified ·
1 Parent(s): c20a994

Add files using upload-large-folder tool

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. README.md +5 -0
  3. config.json +171 -0
  4. generation_config.json +13 -0
  5. merges.txt +0 -0
  6. model.safetensors-00037-of-00094.safetensors +3 -0
  7. model.safetensors-00038-of-00094.safetensors +3 -0
  8. model.safetensors-00039-of-00094.safetensors +3 -0
  9. model.safetensors-00040-of-00094.safetensors +3 -0
  10. model.safetensors-00043-of-00094.safetensors +3 -0
  11. model.safetensors-00044-of-00094.safetensors +3 -0
  12. model.safetensors-00045-of-00094.safetensors +3 -0
  13. model.safetensors-00046-of-00094.safetensors +3 -0
  14. model.safetensors-00047-of-00094.safetensors +3 -0
  15. model.safetensors-00048-of-00094.safetensors +3 -0
  16. model.safetensors-00049-of-00094.safetensors +3 -0
  17. model.safetensors-00050-of-00094.safetensors +3 -0
  18. model.safetensors-00051-of-00094.safetensors +3 -0
  19. model.safetensors-00052-of-00094.safetensors +3 -0
  20. model.safetensors-00053-of-00094.safetensors +3 -0
  21. model.safetensors-00054-of-00094.safetensors +3 -0
  22. model.safetensors-00055-of-00094.safetensors +3 -0
  23. model.safetensors-00056-of-00094.safetensors +3 -0
  24. model.safetensors-00057-of-00094.safetensors +3 -0
  25. model.safetensors-00058-of-00094.safetensors +3 -0
  26. model.safetensors-00061-of-00094.safetensors +3 -0
  27. model.safetensors-00064-of-00094.safetensors +3 -0
  28. model.safetensors-00065-of-00094.safetensors +3 -0
  29. model.safetensors-00066-of-00094.safetensors +3 -0
  30. model.safetensors-00067-of-00094.safetensors +3 -0
  31. model.safetensors-00070-of-00094.safetensors +3 -0
  32. model.safetensors-00071-of-00094.safetensors +3 -0
  33. model.safetensors-00075-of-00094.safetensors +3 -0
  34. model.safetensors-00077-of-00094.safetensors +3 -0
  35. model.safetensors-00078-of-00094.safetensors +3 -0
  36. model.safetensors-00080-of-00094.safetensors +3 -0
  37. model.safetensors-00081-of-00094.safetensors +3 -0
  38. model.safetensors-00082-of-00094.safetensors +3 -0
  39. model.safetensors-00084-of-00094.safetensors +3 -0
  40. model.safetensors-00085-of-00094.safetensors +3 -0
  41. model.safetensors-00087-of-00094.safetensors +3 -0
  42. model.safetensors-00088-of-00094.safetensors +3 -0
  43. model.safetensors-00090-of-00094.safetensors +3 -0
  44. model.safetensors-00091-of-00094.safetensors +3 -0
  45. model.safetensors-00094-of-00094.safetensors +3 -0
  46. model.safetensors.index.json +0 -0
  47. preprocessor_config.json +21 -0
  48. tokenizer.json +3 -0
  49. tokenizer_config.json +305 -0
  50. video_preprocessor_config.json +21 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ ---
5
+ # JGOS-398B-VID
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5_moe",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 248044,
13
+ "full_attention_interval": 4,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "layer_types": [
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "full_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "full_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "full_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "full_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "full_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "full_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "full_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "full_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "full_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "full_attention"
79
+ ],
80
+ "linear_conv_kernel_dim": 4,
81
+ "linear_key_head_dim": 128,
82
+ "linear_num_key_heads": 16,
83
+ "linear_num_value_heads": 64,
84
+ "linear_value_head_dim": 128,
85
+ "max_position_embeddings": 262144,
86
+ "mlp_only_layers": [],
87
+ "model_type": "qwen3_5_moe_text",
88
+ "moe_intermediate_size": 1024,
89
+ "mtp_num_hidden_layers": 1,
90
+ "mtp_use_dedicated_embeddings": false,
91
+ "num_attention_heads": 32,
92
+ "num_experts": 512,
93
+ "num_experts_per_tok": 10,
94
+ "num_hidden_layers": 60,
95
+ "num_key_value_heads": 2,
96
+ "rms_norm_eps": 1e-06,
97
+ "router_aux_loss_coef": 0.001,
98
+ "shared_expert_intermediate_size": 1024,
99
+ "use_cache": true,
100
+ "vocab_size": 248320,
101
+ "mamba_ssm_dtype": "float32",
102
+ "rope_parameters": {
103
+ "mrope_interleaved": true,
104
+ "mrope_section": [
105
+ 11,
106
+ 11,
107
+ 10
108
+ ],
109
+ "rope_type": "default",
110
+ "rope_theta": 10000000,
111
+ "partial_rotary_factor": 0.25
112
+ }
113
+ },
114
+ "tie_word_embeddings": false,
115
+ "transformers_version": "4.57.0.dev0",
116
+ "video_token_id": 248057,
117
+ "vision_config": {
118
+ "deepstack_visual_indexes": [],
119
+ "depth": 27,
120
+ "hidden_act": "gelu_pytorch_tanh",
121
+ "hidden_size": 1152,
122
+ "in_channels": 3,
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 4304,
125
+ "model_type": "qwen3_5_moe",
126
+ "num_heads": 16,
127
+ "num_position_embeddings": 2304,
128
+ "out_hidden_size": 4096,
129
+ "patch_size": 16,
130
+ "spatial_merge_size": 2,
131
+ "temporal_patch_size": 2
132
+ },
133
+ "vision_end_token_id": 248054,
134
+ "vision_start_token_id": 248053,
135
+ "quantization_config": {
136
+ "quant_method": "compressed-tensors",
137
+ "format": "float-quantized",
138
+ "config_groups": {
139
+ "group_0": {
140
+ "targets": [
141
+ "Linear"
142
+ ],
143
+ "weights": {
144
+ "num_bits": 8,
145
+ "type": "float",
146
+ "strategy": "channel",
147
+ "symmetric": true,
148
+ "dynamic": false
149
+ },
150
+ "input_activations": {
151
+ "num_bits": 8,
152
+ "type": "float",
153
+ "strategy": "token",
154
+ "symmetric": true,
155
+ "dynamic": true
156
+ }
157
+ }
158
+ },
159
+ "ignore": [
160
+ "lm_head",
161
+ "re:.*linear_attn.*",
162
+ "re:.*mlp\\.gate$",
163
+ "re:.*shared_expert_gate.*",
164
+ "re:.*norm.*",
165
+ "re:.*embed_tokens.*",
166
+ "re:.*visual.*",
167
+ "re:.*\\.q_norm.*",
168
+ "re:.*\\.k_norm.*"
169
+ ]
170
+ }
171
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.0.dev0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors-00037-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae4d86c40c2f4e100e04f2862254fbd983ac616ac4b5f76100c5058a64b9449
3
+ size 4299161912
model.safetensors-00038-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561f2714a2a6b7be320a23b1a246003c820f61cf5e9deb058eb9d4595dedc539
3
+ size 4299161912
model.safetensors-00039-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf50b5017bd879004a2732888233345a0246029a9a639a9da8520cb962295239
3
+ size 4299161912
model.safetensors-00040-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c58d3203bf600d5fb2c864d8ca0f18f53897d701b6dc2f6df9bc0328c68c206
3
+ size 4299161912
model.safetensors-00043-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6b1ff5226f4a878bcebdf119bfb61b09880b407bfe5b39521a0405381839a4
3
+ size 4299161912
model.safetensors-00044-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ee63cfcbaa3da49424239b938ccf29cb1e6460071795a2541450f023abb748
3
+ size 4299161912
model.safetensors-00045-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec35d67008b60cd218905e3644d93126c427697ade7d5d502a94ab9d985ec1f
3
+ size 4299161904
model.safetensors-00046-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ab1796a67956cea06cf4e648956354c945be6eaf86ce6d7b4f1b34be99b546
3
+ size 4299161912
model.safetensors-00047-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82575961a353a94c5f7603065cbdacf4c10ab3ef5e6b5d89dc69b451068cc760
3
+ size 4299161912
model.safetensors-00048-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cd84f5cfdba7b03aa1d32267e2329ff8f6ca755bf751ed14714d0d3f5ca099
3
+ size 4299161912
model.safetensors-00049-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5443df6b1729e3a3c394577b43b9054ec5ba0fb331864c20e44aa822f7b990d3
3
+ size 4299161912
model.safetensors-00050-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988d4fd007dbe1287ed3a6f3df045d181ffaf11067dd4553afe9c62eb57e2ea8
3
+ size 4299161912
model.safetensors-00051-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b545e3a5fa1d23b0586e330dedc251c619c299df3fe7722a7b465abea26f6b8c
3
+ size 4299161912
model.safetensors-00052-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b71bc0f009b7ba95c99bad6bcb1c65eb5c88a0c7e3ee8f096df40b451299f4b
3
+ size 4299161912
model.safetensors-00053-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e99af0cdad48b2ed03293fff380f4bcca3816c95a90dacf916a38678234e6b
3
+ size 4299161912
model.safetensors-00054-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace8607a148ff203dcdd811de62dd32618b8c1764083aded0d02173751b2c11b
3
+ size 4299161912
model.safetensors-00055-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f97ea580efc65ed4430ca8c3d73c37c7916773d03a37aa9bc39adea0de4548
3
+ size 4299161912
model.safetensors-00056-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337e10c33113ae54eb573324269d0f4d91bf7ac5bf0d370fe38d1c797b6549a3
3
+ size 4299161912
model.safetensors-00057-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d995b4b39f0f27a7bc4adb98049d562e7e4c67f3350234863f792b39350fd41
3
+ size 4299161912
model.safetensors-00058-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da028c7d45cf5d641eed6b099dc0255cac448b5ddb3c8b0b6995902156d60c7
3
+ size 4299161912
model.safetensors-00061-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b37263dc5e29f490b4830e4166644ec85feb56d11f225aeef71e0fdba6d942a
3
+ size 4311745088
model.safetensors-00064-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6558f0c50cddb2357f775b0af2be426df3dfa225b01345caf3e46930041ad766
3
+ size 4311745088
model.safetensors-00065-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c37d1c6f4d936b25e9cceb41bd2bbdd526b54a2d428200f0280fa23b6f75599
3
+ size 4311745088
model.safetensors-00066-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5314be0b6b4d1a9165105e4ae4796dae7e02b1fd78b73ba5ba28e005f7dc7a11
3
+ size 4311745088
model.safetensors-00067-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0655917274b851b0d4c6ba1d61357a39433a656fed9d96fac4e5fbcfd00ee2
3
+ size 4311745088
model.safetensors-00070-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b532d3ceb129d3affb39ca15bd40ca03b2c284ca89dc8fb93f0dd9a525f4ba
3
+ size 4311745088
model.safetensors-00071-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584f3755d8226ccd227f89a48b10d1867a8ecc97ceb99c752afc37378c6a564d
3
+ size 4311745088
model.safetensors-00075-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff51f5dc1035f2652dd1bb0955494cc78afd2d1a13e0b2929c3168d27b460010
3
+ size 4311745088
model.safetensors-00077-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb1ab4d641491f6a24b1feec48a57e72715c7006fbae5d045796401444a1549
3
+ size 4311745088
model.safetensors-00078-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3692f10448cff7d229355d035ede1177009509b0233b9c22aa3f0338c52c4296
3
+ size 4311745088
model.safetensors-00080-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ca3e591cebcb9847224ea47654a63b4eb50008aeb1ac823c2ed70f69199448
3
+ size 4311745088
model.safetensors-00081-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f104a5b5a5973bec6ea67b2cbf64b6248de6cb3bcfa5bbf9bc90d63eaa6a3c2f
3
+ size 4311745088
model.safetensors-00082-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3b34983ce6daae679df519ff5004edc582ac144777edae2d172f1f7f997ac5
3
+ size 4311745088
model.safetensors-00084-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f34a30cb4e654396ea4f069a674ee4edcee96a1a285b58ede5165fc2b39eca
3
+ size 4311745088
model.safetensors-00085-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328d84444a68cbb854863aca224d21c2ada211607f279460df0a00f415a83fb8
3
+ size 4311745088
model.safetensors-00087-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e49b4013129cd7da8a52ab553b3045a5d99e7f2b5be95aeb92cdbb312f57fb4
3
+ size 4311745088
model.safetensors-00088-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f76aec810f0718996407afd6575eee492a00c90744de6621af4090384ae1eb
3
+ size 4311745088
model.safetensors-00090-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7caea2705a367a2d7a74c48393a0cbf8bb96377ffbcd8d994a2f352672e8ce6
3
+ size 4311745088
model.safetensors-00091-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b367d427d788fcab2d56a62a9f3c93164cb4df78fb72575a308527a24bba751e
3
+ size 8632869792
model.safetensors-00094-of-00094.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d26f47e9ef06271f3a448cf49bce606ae7e399e89e4a8660b5c8b2ffd3ee5f
3
+ size 4000125000
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }