Hugging Face's logo

shahidchdry
/
lovelake-router-4b

Image-Text-to-Text
Transformers
Safetensors
English
qwen3_5
text-generation-inference
unsloth
Model card Files
xet
 Community
shahidchdry commited on
Commit
fc5c204
·
verified ·
1 Parent(s): b598e24

(Trained with Unsloth)

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. config.json +112 -0
  3. generation_config.json +7 -0
  4. processor_config.json +63 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +299 -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
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "torch_dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_name": "unsloth/Qwen3.5-4B-Base",
8
+ "model_type": "qwen3_5",
9
+ "pad_token_id": 248055,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "attn_output_gate": true,
14
+ "bos_token_id": null,
15
+ "torch_dtype": "bfloat16",
16
+ "eos_token_id": 248044,
17
+ "full_attention_interval": 4,
18
+ "head_dim": 256,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 2560,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 9216,
23
+ "layer_types": [
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention"
56
+ ],
57
+ "linear_conv_kernel_dim": 4,
58
+ "linear_key_head_dim": 128,
59
+ "linear_num_key_heads": 16,
60
+ "linear_num_value_heads": 32,
61
+ "linear_value_head_dim": 128,
62
+ "mamba_ssm_dtype": "float32",
63
+ "max_position_embeddings": 262144,
64
+ "mlp_only_layers": [],
65
+ "model_type": "qwen3_5_text",
66
+ "mtp_num_hidden_layers": 1,
67
+ "mtp_use_dedicated_embeddings": false,
68
+ "num_attention_heads": 16,
69
+ "num_hidden_layers": 32,
70
+ "num_key_value_heads": 4,
71
+ "pad_token_id": null,
72
+ "partial_rotary_factor": 0.25,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_parameters": {
75
+ "mrope_interleaved": true,
76
+ "mrope_section": [
77
+ 11,
78
+ 11,
79
+ 10
80
+ ],
81
+ "partial_rotary_factor": 0.25,
82
+ "rope_theta": 10000000,
83
+ "rope_type": "default"
84
+ },
85
+ "tie_word_embeddings": true,
86
+ "use_cache": true,
87
+ "vocab_size": 248320
88
+ },
89
+ "tie_word_embeddings": true,
90
+ "unsloth_fixed": true,
91
+ "unsloth_version": "2026.6.1",
92
+ "video_token_id": 248057,
93
+ "vision_config": {
94
+ "deepstack_visual_indexes": [],
95
+ "depth": 24,
96
+ "torch_dtype": "bfloat16",
97
+ "hidden_act": "gelu_pytorch_tanh",
98
+ "hidden_size": 1024,
99
+ "in_channels": 3,
100
+ "initializer_range": 0.02,
101
+ "intermediate_size": 4096,
102
+ "model_type": "qwen3_5",
103
+ "num_heads": 16,
104
+ "num_position_embeddings": 2304,
105
+ "out_hidden_size": 2560,
106
+ "patch_size": 16,
107
+ "spatial_merge_size": 2,
108
+ "temporal_patch_size": 2
109
+ },
110
+ "vision_end_token_id": 248054,
111
+ "vision_start_token_id": 248053
112
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 248044,
4
+ "pad_token_id": 248055,
5
+ "transformers_version": "5.3.0",
6
+ "use_cache": true
7
+ }
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 234881024,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|endoftext|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|vision_pad|>",
24
+ "padding_side": "left",
25
+ "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+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>",
33
+ "added_tokens_decoder": {
34
+ "248044": {
35
+ "content": "<|endoftext|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "248045": {
43
+ "content": "<|im_start|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "248046": {
51
+ "content": "<|im_end|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "248047": {
59
+ "content": "<|object_ref_start|>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "248048": {
67
+ "content": "<|object_ref_end|>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "248049": {
75
+ "content": "<|box_start|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "248050": {
83
+ "content": "<|box_end|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "248051": {
91
+ "content": "<|quad_start|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "248052": {
99
+ "content": "<|quad_end|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "248053": {
107
+ "content": "<|vision_start|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "248054": {
115
+ "content": "<|vision_end|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "248055": {
123
+ "content": "<|vision_pad|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "248056": {
131
+ "content": "<|image_pad|>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "248057": {
139
+ "content": "<|video_pad|>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "248058": {
147
+ "content": "<tool_call>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": false
153
+ },
154
+ "248059": {
155
+ "content": "</tool_call>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": false
161
+ },
162
+ "248060": {
163
+ "content": "<|fim_prefix|>",
164
+ "single_word": false,
165
+ "lstrip": false,
166
+ "rstrip": false,
167
+ "normalized": false,
168
+ "special": false
169
+ },
170
+ "248061": {
171
+ "content": "<|fim_middle|>",
172
+ "single_word": false,
173
+ "lstrip": false,
174
+ "rstrip": false,
175
+ "normalized": false,
176
+ "special": false
177
+ },
178
+ "248062": {
179
+ "content": "<|fim_suffix|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ "248063": {
187
+ "content": "<|fim_pad|>",
188
+ "single_word": false,
189
+ "lstrip": false,
190
+ "rstrip": false,
191
+ "normalized": false,
192
+ "special": false
193
+ },
194
+ "248064": {
195
+ "content": "<|repo_name|>",
196
+ "single_word": false,
197
+ "lstrip": false,
198
+ "rstrip": false,
199
+ "normalized": false,
200
+ "special": false
201
+ },
202
+ "248065": {
203
+ "content": "<|file_sep|>",
204
+ "single_word": false,
205
+ "lstrip": false,
206
+ "rstrip": false,
207
+ "normalized": false,
208
+ "special": false
209
+ },
210
+ "248066": {
211
+ "content": "<tool_response>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": false
217
+ },
218
+ "248067": {
219
+ "content": "</tool_response>",
220
+ "single_word": false,
221
+ "lstrip": false,
222
+ "rstrip": false,
223
+ "normalized": false,
224
+ "special": false
225
+ },
226
+ "248068": {
227
+ "content": "<think>",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": false,
232
+ "special": false
233
+ },
234
+ "248069": {
235
+ "content": "</think>",
236
+ "single_word": false,
237
+ "lstrip": false,
238
+ "rstrip": false,
239
+ "normalized": false,
240
+ "special": false
241
+ },
242
+ "248070": {
243
+ "content": "<|audio_start|>",
244
+ "single_word": false,
245
+ "lstrip": false,
246
+ "rstrip": false,
247
+ "normalized": false,
248
+ "special": true
249
+ },
250
+ "248071": {
251
+ "content": "<|audio_end|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ "248072": {
259
+ "content": "<tts_pad>",
260
+ "single_word": false,
261
+ "lstrip": false,
262
+ "rstrip": false,
263
+ "normalized": false,
264
+ "special": true
265
+ },
266
+ "248073": {
267
+ "content": "<tts_text_bos>",
268
+ "single_word": false,
269
+ "lstrip": false,
270
+ "rstrip": false,
271
+ "normalized": false,
272
+ "special": true
273
+ },
274
+ "248074": {
275
+ "content": "<tts_text_eod>",
276
+ "single_word": false,
277
+ "lstrip": false,
278
+ "rstrip": false,
279
+ "normalized": false,
280
+ "special": true
281
+ },
282
+ "248075": {
283
+ "content": "<tts_text_bos_single>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ "248076": {
291
+ "content": "<|audio_pad|>",
292
+ "single_word": false,
293
+ "lstrip": false,
294
+ "rstrip": false,
295
+ "normalized": false,
296
+ "special": true
297
+ }
298
+ }
299
+ }