hermeschen-ezcon commited on
Commit
c3f593d
·
verified ·
1 Parent(s): c0bbf06

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. config.json +27 -198
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
  ---
11
 
12
  # EZCon/Huihui-Qwen3-VL-4B-Instruct-abliterated-mlx
13
- This model was converted to MLX format from [`huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated`]() using mlx-vlm version **0.3.4**.
14
  Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated) for more details on the model.
15
  ## Use with mlx
16
 
 
10
  ---
11
 
12
  # EZCon/Huihui-Qwen3-VL-4B-Instruct-abliterated-mlx
13
+ This model was converted to MLX format from [`huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated`]() using mlx-vlm version **0.3.3**.
14
  Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated) for more details on the model.
15
  ## Use with mlx
16
 
config.json CHANGED
@@ -1,72 +1,27 @@
1
  {
2
- "add_cross_attention": false,
3
  "architectures": [
4
  "Qwen3VLForConditionalGeneration"
5
  ],
6
- "bad_words_ids": null,
7
- "begin_suppress_tokens": null,
8
- "bos_token_id": null,
9
- "chunk_size_feed_forward": 0,
10
- "cross_attention_hidden_size": null,
11
- "decoder_start_token_id": null,
12
- "diversity_penalty": 0.0,
13
- "do_sample": false,
14
  "dtype": "bfloat16",
15
- "early_stopping": false,
16
- "encoder_no_repeat_ngram_size": 0,
17
- "eos_token_id": null,
18
- "exponential_decay_length_penalty": null,
19
- "finetuning_task": null,
20
- "forced_bos_token_id": null,
21
- "forced_eos_token_id": null,
22
- "id2label": {
23
- "0": "LABEL_0",
24
- "1": "LABEL_1"
25
- },
26
  "image_token_id": 151655,
27
- "is_decoder": false,
28
- "is_encoder_decoder": false,
29
- "label2id": {
30
- "LABEL_0": 0,
31
- "LABEL_1": 1
32
- },
33
- "length_penalty": 1.0,
34
- "max_length": 20,
35
- "min_length": 0,
36
  "model_type": "qwen3_vl",
37
- "no_repeat_ngram_size": 0,
38
- "num_beam_groups": 1,
39
- "num_beams": 1,
40
- "num_return_sequences": 1,
41
- "output_attentions": false,
42
- "output_hidden_states": false,
43
- "output_scores": false,
44
- "pad_token_id": null,
45
- "prefix": null,
46
- "problem_type": null,
47
- "pruned_heads": {},
48
- "remove_invalid_values": false,
49
- "repetition_penalty": 1.0,
50
- "return_dict": true,
51
- "return_dict_in_generate": false,
52
- "sep_token_id": null,
53
- "suppress_tokens": null,
54
- "task_specific_params": null,
55
- "temperature": 1.0,
56
  "text_config": {
57
- "vocab_size": 151936,
58
- "max_position_embeddings": 262144,
 
 
 
 
 
59
  "hidden_size": 2560,
 
60
  "intermediate_size": 9728,
61
- "num_hidden_layers": 36,
 
62
  "num_attention_heads": 32,
 
63
  "num_key_value_heads": 8,
64
- "head_dim": 128,
65
- "hidden_act": "silu",
66
- "initializer_range": 0.02,
67
  "rms_norm_eps": 1e-06,
68
- "use_cache": true,
69
- "rope_theta": 5000000,
70
  "rope_scaling": {
71
  "mrope_interleaved": true,
72
  "mrope_section": [
@@ -76,160 +31,34 @@
76
  ],
77
  "rope_type": "default"
78
  },
79
- "attention_bias": false,
80
- "attention_dropout": 0.0,
81
- "return_dict": true,
82
- "output_hidden_states": false,
83
- "torchscript": false,
84
- "dtype": "bfloat16",
85
- "pruned_heads": {},
86
  "tie_word_embeddings": true,
87
- "chunk_size_feed_forward": 0,
88
- "is_encoder_decoder": false,
89
- "is_decoder": false,
90
- "cross_attention_hidden_size": null,
91
- "add_cross_attention": false,
92
- "tie_encoder_decoder": false,
93
- "architectures": null,
94
- "finetuning_task": null,
95
- "id2label": {
96
- "0": "LABEL_0",
97
- "1": "LABEL_1"
98
- },
99
- "label2id": {
100
- "LABEL_0": 0,
101
- "LABEL_1": 1
102
- },
103
- "task_specific_params": null,
104
- "problem_type": null,
105
- "tokenizer_class": null,
106
- "prefix": null,
107
- "bos_token_id": 151643,
108
- "pad_token_id": null,
109
- "eos_token_id": 151645,
110
- "sep_token_id": null,
111
- "decoder_start_token_id": null,
112
- "max_length": 20,
113
- "min_length": 0,
114
- "do_sample": false,
115
- "early_stopping": false,
116
- "num_beams": 1,
117
- "temperature": 1.0,
118
- "top_k": 50,
119
- "top_p": 1.0,
120
- "typical_p": 1.0,
121
- "repetition_penalty": 1.0,
122
- "length_penalty": 1.0,
123
- "no_repeat_ngram_size": 0,
124
- "encoder_no_repeat_ngram_size": 0,
125
- "bad_words_ids": null,
126
- "num_return_sequences": 1,
127
- "output_scores": false,
128
- "return_dict_in_generate": false,
129
- "forced_bos_token_id": null,
130
- "forced_eos_token_id": null,
131
- "remove_invalid_values": false,
132
- "exponential_decay_length_penalty": null,
133
- "suppress_tokens": null,
134
- "begin_suppress_tokens": null,
135
- "num_beam_groups": 1,
136
- "diversity_penalty": 0.0,
137
- "_name_or_path": "",
138
- "model_type": "qwen3_vl_text",
139
- "tf_legacy_loss": false,
140
- "use_bfloat16": false,
141
- "output_attentions": false
142
  },
143
- "tf_legacy_loss": false,
144
- "tie_encoder_decoder": false,
145
  "tie_word_embeddings": true,
146
- "tokenizer_class": null,
147
- "top_k": 50,
148
- "top_p": 1.0,
149
- "torchscript": false,
150
  "transformers_version": "4.57.1",
151
- "typical_p": 1.0,
152
- "use_bfloat16": false,
153
  "video_token_id": 151656,
154
  "vision_config": {
155
- "return_dict": true,
156
- "output_hidden_states": false,
157
- "torchscript": false,
158
- "dtype": "bfloat16",
159
- "pruned_heads": {},
160
- "tie_word_embeddings": true,
161
- "chunk_size_feed_forward": 0,
162
- "is_encoder_decoder": false,
163
- "is_decoder": false,
164
- "cross_attention_hidden_size": null,
165
- "add_cross_attention": false,
166
- "tie_encoder_decoder": false,
167
- "architectures": null,
168
- "finetuning_task": null,
169
- "id2label": {
170
- "0": "LABEL_0",
171
- "1": "LABEL_1"
172
- },
173
- "label2id": {
174
- "LABEL_0": 0,
175
- "LABEL_1": 1
176
- },
177
- "task_specific_params": null,
178
- "problem_type": null,
179
- "tokenizer_class": null,
180
- "prefix": null,
181
- "bos_token_id": null,
182
- "pad_token_id": null,
183
- "eos_token_id": null,
184
- "sep_token_id": null,
185
- "decoder_start_token_id": null,
186
- "max_length": 20,
187
- "min_length": 0,
188
- "do_sample": false,
189
- "early_stopping": false,
190
- "num_beams": 1,
191
- "temperature": 1.0,
192
- "top_k": 50,
193
- "top_p": 1.0,
194
- "typical_p": 1.0,
195
- "repetition_penalty": 1.0,
196
- "length_penalty": 1.0,
197
- "no_repeat_ngram_size": 0,
198
- "encoder_no_repeat_ngram_size": 0,
199
- "bad_words_ids": null,
200
- "num_return_sequences": 1,
201
- "output_scores": false,
202
- "return_dict_in_generate": false,
203
- "forced_bos_token_id": null,
204
- "forced_eos_token_id": null,
205
- "remove_invalid_values": false,
206
- "exponential_decay_length_penalty": null,
207
- "suppress_tokens": null,
208
- "begin_suppress_tokens": null,
209
- "num_beam_groups": 1,
210
- "diversity_penalty": 0.0,
211
- "_name_or_path": "",
212
- "model_type": "qwen3_vl",
213
- "tf_legacy_loss": false,
214
- "use_bfloat16": false,
215
  "depth": 24,
216
- "hidden_size": 1024,
217
  "hidden_act": "gelu_pytorch_tanh",
 
 
 
218
  "intermediate_size": 4096,
 
219
  "num_heads": 16,
220
- "in_channels": 3,
 
221
  "patch_size": 16,
222
  "spatial_merge_size": 2,
223
- "temporal_patch_size": 2,
224
- "out_hidden_size": 2560,
225
- "num_position_embeddings": 2304,
226
- "initializer_range": 0.02,
227
- "deepstack_visual_indexes": [
228
- 5,
229
- 11,
230
- 17
231
- ],
232
- "output_attentions": false
233
  },
234
  "vision_end_token_id": 151653,
235
  "vision_start_token_id": 151652
 
1
  {
 
2
  "architectures": [
3
  "Qwen3VLForConditionalGeneration"
4
  ],
 
 
 
 
 
 
 
 
5
  "dtype": "bfloat16",
 
 
 
 
 
 
 
 
 
 
 
6
  "image_token_id": 151655,
 
 
 
 
 
 
 
 
 
7
  "model_type": "qwen3_vl",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 151643,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 151645,
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
  "hidden_size": 2560,
17
+ "initializer_range": 0.02,
18
  "intermediate_size": 9728,
19
+ "max_position_embeddings": 262144,
20
+ "model_type": "qwen3_vl_text",
21
  "num_attention_heads": 32,
22
+ "num_hidden_layers": 36,
23
  "num_key_value_heads": 8,
 
 
 
24
  "rms_norm_eps": 1e-06,
 
 
25
  "rope_scaling": {
26
  "mrope_interleaved": true,
27
  "mrope_section": [
 
31
  ],
32
  "rope_type": "default"
33
  },
34
+ "rope_theta": 5000000,
 
 
 
 
 
 
35
  "tie_word_embeddings": true,
36
+ "use_cache": true,
37
+ "vocab_size": 151936
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  },
 
 
39
  "tie_word_embeddings": true,
 
 
 
 
40
  "transformers_version": "4.57.1",
 
 
41
  "video_token_id": 151656,
42
  "vision_config": {
43
+ "deepstack_visual_indexes": [
44
+ 5,
45
+ 11,
46
+ 17
47
+ ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  "depth": 24,
49
+ "dtype": "bfloat16",
50
  "hidden_act": "gelu_pytorch_tanh",
51
+ "hidden_size": 1024,
52
+ "in_channels": 3,
53
+ "initializer_range": 0.02,
54
  "intermediate_size": 4096,
55
+ "model_type": "qwen3_vl",
56
  "num_heads": 16,
57
+ "num_position_embeddings": 2304,
58
+ "out_hidden_size": 2560,
59
  "patch_size": 16,
60
  "spatial_merge_size": 2,
61
+ "temporal_patch_size": 2
 
 
 
 
 
 
 
 
 
62
  },
63
  "vision_end_token_id": 151653,
64
  "vision_start_token_id": 151652