Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- config.json +593 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quant_log.csv +197 -0
- quantize_config.json +21 -0
- special_tokens_map.json +25 -0
- tokenizer.json +3 -0
- tokenizer_config.json +209 -0
- vocab.json +0 -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
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|AUDIO|>": 151646,
|
5 |
+
"<|IMAGE|>": 151655,
|
6 |
+
"<|VIDEO|>": 151656,
|
7 |
+
"<|audio_bos|>": 151647,
|
8 |
+
"<|audio_eos|>": 151648,
|
9 |
+
"<|box_end|>": 151649,
|
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 |
+
"<|quad_end|>": 151651,
|
19 |
+
"<|quad_start|>": 151650,
|
20 |
+
"<|repo_name|>": 151663,
|
21 |
+
"<|vision_bos|>": 151652,
|
22 |
+
"<|vision_eos|>": 151653,
|
23 |
+
"<|vision_pad|>": 151654
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,593 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen2_5OmniModel"
|
4 |
+
],
|
5 |
+
"enable_audio_output": true,
|
6 |
+
"enable_talker": true,
|
7 |
+
"model_type": "qwen2_5_omni",
|
8 |
+
"quantization_config": {
|
9 |
+
"bits": 4,
|
10 |
+
"checkpoint_format": "gptq",
|
11 |
+
"desc_act": true,
|
12 |
+
"group_size": 128,
|
13 |
+
"lm_head": false,
|
14 |
+
"meta": {
|
15 |
+
"damp_auto_increment": 0.0025,
|
16 |
+
"damp_percent": 0.01,
|
17 |
+
"mse": 0.0,
|
18 |
+
"quantizer": [
|
19 |
+
"gptqmodel:2.1.1-dev"
|
20 |
+
],
|
21 |
+
"static_groups": false,
|
22 |
+
"true_sequential": true,
|
23 |
+
"uri": "https://github.com/modelcloud/gptqmodel"
|
24 |
+
},
|
25 |
+
"pack_dtype": "int32",
|
26 |
+
"quant_method": "gptq",
|
27 |
+
"sym": true
|
28 |
+
},
|
29 |
+
"talker_config": {
|
30 |
+
"_attn_implementation_autoset": true,
|
31 |
+
"_name_or_path": "Qwen2.5-Omni-7B/talker",
|
32 |
+
"architectures": [
|
33 |
+
"Qwen2OmniTalkerForConditionalGeneration"
|
34 |
+
],
|
35 |
+
"attention_dropout": 0.0,
|
36 |
+
"audio_end_token_id": 151648,
|
37 |
+
"audio_start_token_id": 151647,
|
38 |
+
"audio_token_index": 151646,
|
39 |
+
"embedding_size": 3584,
|
40 |
+
"head_dim": 128,
|
41 |
+
"hidden_act": "silu",
|
42 |
+
"hidden_size": 896,
|
43 |
+
"image_token_index": 151655,
|
44 |
+
"init_std": 0.02,
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"intermediate_size": 18944,
|
47 |
+
"max_position_embeddings": 32768,
|
48 |
+
"max_window_layers": 28,
|
49 |
+
"model_type": "qwen2_5_omni_talker",
|
50 |
+
"num_attention_heads": 12,
|
51 |
+
"num_hidden_layers": 24,
|
52 |
+
"num_key_value_heads": 4,
|
53 |
+
"position_id_per_seconds": 25,
|
54 |
+
"rms_norm_eps": 1e-06,
|
55 |
+
"rope_scaling": {
|
56 |
+
"mrope_section": [
|
57 |
+
16,
|
58 |
+
24,
|
59 |
+
24
|
60 |
+
],
|
61 |
+
"rope_type": "default",
|
62 |
+
"type": "default"
|
63 |
+
},
|
64 |
+
"rope_theta": 1000000.0,
|
65 |
+
"seconds_per_chunk": 2,
|
66 |
+
"sliding_window": 32768,
|
67 |
+
"spatial_merge_size": 2,
|
68 |
+
"torch_dtype": "float16",
|
69 |
+
"tts_codec_end_token_id": 8294,
|
70 |
+
"tts_codec_mask_token_id": 8296,
|
71 |
+
"tts_codec_pad_token_id": 8292,
|
72 |
+
"tts_codec_start_token_id": 8293,
|
73 |
+
"tts_text_end_token_id": 151861,
|
74 |
+
"tts_text_pad_token_id": 151859,
|
75 |
+
"tts_text_start_token_id": 151860,
|
76 |
+
"use_cache": true,
|
77 |
+
"use_mrope": false,
|
78 |
+
"use_sliding_window": false,
|
79 |
+
"video_token_index": 151656,
|
80 |
+
"vision_end_token_id": 151653,
|
81 |
+
"vision_start_token_id": 151652,
|
82 |
+
"vocab_size": 8448
|
83 |
+
},
|
84 |
+
"thinker_config": {
|
85 |
+
"_attn_implementation_autoset": true,
|
86 |
+
"_name_or_path": "Qwen2.5-Omni-7B/thinker",
|
87 |
+
"architectures": [
|
88 |
+
"Qwen2OmniNaViTThinkerForConditionalGeneration"
|
89 |
+
],
|
90 |
+
"audio_config": {
|
91 |
+
"_attn_implementation_autoset": true,
|
92 |
+
"_name_or_path": "",
|
93 |
+
"activation_dropout": 0.0,
|
94 |
+
"activation_function": "gelu",
|
95 |
+
"add_cross_attention": false,
|
96 |
+
"architectures": null,
|
97 |
+
"attention_dropout": 0.0,
|
98 |
+
"bad_words_ids": null,
|
99 |
+
"begin_suppress_tokens": null,
|
100 |
+
"bos_token_id": null,
|
101 |
+
"chunk_size_feed_forward": 0,
|
102 |
+
"cross_attention_hidden_size": null,
|
103 |
+
"d_model": 1280,
|
104 |
+
"decoder_start_token_id": null,
|
105 |
+
"diversity_penalty": 0.0,
|
106 |
+
"do_sample": false,
|
107 |
+
"dropout": 0.0,
|
108 |
+
"early_stopping": false,
|
109 |
+
"encoder_attention_heads": 20,
|
110 |
+
"encoder_ffn_dim": 5120,
|
111 |
+
"encoder_layerdrop": 0.0,
|
112 |
+
"encoder_layers": 32,
|
113 |
+
"encoder_no_repeat_ngram_size": 0,
|
114 |
+
"eos_token_id": null,
|
115 |
+
"exponential_decay_length_penalty": null,
|
116 |
+
"finetuning_task": null,
|
117 |
+
"forced_bos_token_id": null,
|
118 |
+
"forced_eos_token_id": null,
|
119 |
+
"id2label": {
|
120 |
+
"0": "LABEL_0",
|
121 |
+
"1": "LABEL_1"
|
122 |
+
},
|
123 |
+
"init_std": 0.02,
|
124 |
+
"is_decoder": false,
|
125 |
+
"is_encoder_decoder": false,
|
126 |
+
"label2id": {
|
127 |
+
"LABEL_0": 0,
|
128 |
+
"LABEL_1": 1
|
129 |
+
},
|
130 |
+
"length_penalty": 1.0,
|
131 |
+
"max_length": 20,
|
132 |
+
"max_source_positions": 1500,
|
133 |
+
"min_length": 0,
|
134 |
+
"model_type": "qwen2_5_omni_audio_encoder",
|
135 |
+
"n_window": 100,
|
136 |
+
"no_repeat_ngram_size": 0,
|
137 |
+
"num_beam_groups": 1,
|
138 |
+
"num_beams": 1,
|
139 |
+
"num_hidden_layers": 32,
|
140 |
+
"num_mel_bins": 128,
|
141 |
+
"num_return_sequences": 1,
|
142 |
+
"output_attentions": false,
|
143 |
+
"output_dim": 3584,
|
144 |
+
"output_hidden_states": false,
|
145 |
+
"output_scores": false,
|
146 |
+
"pad_token_id": null,
|
147 |
+
"prefix": null,
|
148 |
+
"problem_type": null,
|
149 |
+
"pruned_heads": {},
|
150 |
+
"remove_invalid_values": false,
|
151 |
+
"repetition_penalty": 1.0,
|
152 |
+
"return_dict": true,
|
153 |
+
"return_dict_in_generate": false,
|
154 |
+
"scale_embedding": false,
|
155 |
+
"sep_token_id": null,
|
156 |
+
"suppress_tokens": null,
|
157 |
+
"task_specific_params": null,
|
158 |
+
"temperature": 1.0,
|
159 |
+
"tf_legacy_loss": false,
|
160 |
+
"tie_encoder_decoder": false,
|
161 |
+
"tie_word_embeddings": true,
|
162 |
+
"tokenizer_class": null,
|
163 |
+
"top_k": 50,
|
164 |
+
"top_p": 1.0,
|
165 |
+
"torch_dtype": null,
|
166 |
+
"torchscript": false,
|
167 |
+
"typical_p": 1.0,
|
168 |
+
"use_bfloat16": false
|
169 |
+
},
|
170 |
+
"audio_end_token_id": 151648,
|
171 |
+
"audio_start_token_id": 151647,
|
172 |
+
"audio_token_index": 151646,
|
173 |
+
"bos_token_id": 151644,
|
174 |
+
"eos_token_id": 151645,
|
175 |
+
"ignore_index": -100,
|
176 |
+
"image_token_index": 151655,
|
177 |
+
"init_std": 0.02,
|
178 |
+
"model_type": "qwen2_5_omni_thinker",
|
179 |
+
"pad_token_id": 151643,
|
180 |
+
"position_id_per_seconds": 25,
|
181 |
+
"seconds_per_chunk": 2,
|
182 |
+
"text_config": {
|
183 |
+
"_attn_implementation_autoset": false,
|
184 |
+
"_name_or_path": "",
|
185 |
+
"add_cross_attention": false,
|
186 |
+
"architectures": null,
|
187 |
+
"attention_dropout": 0.0,
|
188 |
+
"bad_words_ids": null,
|
189 |
+
"begin_suppress_tokens": null,
|
190 |
+
"bos_token_id": null,
|
191 |
+
"chunk_size_feed_forward": 0,
|
192 |
+
"cross_attention_hidden_size": null,
|
193 |
+
"decoder_start_token_id": null,
|
194 |
+
"diversity_penalty": 0.0,
|
195 |
+
"do_sample": false,
|
196 |
+
"early_stopping": false,
|
197 |
+
"encoder_no_repeat_ngram_size": 0,
|
198 |
+
"eos_token_id": null,
|
199 |
+
"exponential_decay_length_penalty": null,
|
200 |
+
"finetuning_task": null,
|
201 |
+
"forced_bos_token_id": null,
|
202 |
+
"forced_eos_token_id": null,
|
203 |
+
"hidden_act": "silu",
|
204 |
+
"hidden_size": 3584,
|
205 |
+
"id2label": {
|
206 |
+
"0": "LABEL_0",
|
207 |
+
"1": "LABEL_1"
|
208 |
+
},
|
209 |
+
"init_std": 0.02,
|
210 |
+
"intermediate_size": 18944,
|
211 |
+
"is_decoder": false,
|
212 |
+
"is_encoder_decoder": false,
|
213 |
+
"label2id": {
|
214 |
+
"LABEL_0": 0,
|
215 |
+
"LABEL_1": 1
|
216 |
+
},
|
217 |
+
"length_penalty": 1.0,
|
218 |
+
"max_length": 20,
|
219 |
+
"max_position_embeddings": 32768,
|
220 |
+
"max_window_layers": 28,
|
221 |
+
"min_length": 0,
|
222 |
+
"model_type": "qwen2_5_omni_text",
|
223 |
+
"no_repeat_ngram_size": 0,
|
224 |
+
"num_attention_heads": 28,
|
225 |
+
"num_beam_groups": 1,
|
226 |
+
"num_beams": 1,
|
227 |
+
"num_hidden_layers": 28,
|
228 |
+
"num_key_value_heads": 4,
|
229 |
+
"num_return_sequences": 1,
|
230 |
+
"output_attentions": false,
|
231 |
+
"output_hidden_states": false,
|
232 |
+
"output_scores": false,
|
233 |
+
"pad_token_id": null,
|
234 |
+
"prefix": null,
|
235 |
+
"problem_type": null,
|
236 |
+
"pruned_heads": {},
|
237 |
+
"remove_invalid_values": false,
|
238 |
+
"repetition_penalty": 1.0,
|
239 |
+
"return_dict": true,
|
240 |
+
"return_dict_in_generate": false,
|
241 |
+
"rms_norm_eps": 1e-06,
|
242 |
+
"rope_scaling": {
|
243 |
+
"mrope_section": [
|
244 |
+
16,
|
245 |
+
24,
|
246 |
+
24
|
247 |
+
],
|
248 |
+
"rope_type": "default",
|
249 |
+
"type": "default"
|
250 |
+
},
|
251 |
+
"rope_theta": 1000000.0,
|
252 |
+
"sep_token_id": null,
|
253 |
+
"sliding_window": 32768,
|
254 |
+
"suppress_tokens": null,
|
255 |
+
"task_specific_params": null,
|
256 |
+
"temperature": 1.0,
|
257 |
+
"tf_legacy_loss": false,
|
258 |
+
"tie_encoder_decoder": false,
|
259 |
+
"tie_word_embeddings": true,
|
260 |
+
"tokenizer_class": null,
|
261 |
+
"top_k": 50,
|
262 |
+
"top_p": 1.0,
|
263 |
+
"torch_dtype": null,
|
264 |
+
"torchscript": false,
|
265 |
+
"typical_p": 1.0,
|
266 |
+
"use_bfloat16": false,
|
267 |
+
"use_cache": true,
|
268 |
+
"use_sliding_window": false,
|
269 |
+
"vocab_size": 152064
|
270 |
+
},
|
271 |
+
"torch_dtype": "float16",
|
272 |
+
"use_mrope": false,
|
273 |
+
"user_token_id": 872,
|
274 |
+
"video_token_index": 151656,
|
275 |
+
"vision_config": {
|
276 |
+
"_attn_implementation_autoset": true,
|
277 |
+
"_name_or_path": "",
|
278 |
+
"add_cross_attention": false,
|
279 |
+
"architectures": null,
|
280 |
+
"bad_words_ids": null,
|
281 |
+
"begin_suppress_tokens": null,
|
282 |
+
"bos_token_id": null,
|
283 |
+
"chunk_size_feed_forward": 0,
|
284 |
+
"cross_attention_hidden_size": null,
|
285 |
+
"decoder_start_token_id": null,
|
286 |
+
"depth": 32,
|
287 |
+
"diversity_penalty": 0.0,
|
288 |
+
"do_sample": false,
|
289 |
+
"early_stopping": false,
|
290 |
+
"embed_dim": 1280,
|
291 |
+
"encoder_no_repeat_ngram_size": 0,
|
292 |
+
"eos_token_id": null,
|
293 |
+
"exponential_decay_length_penalty": null,
|
294 |
+
"finetuning_task": null,
|
295 |
+
"forced_bos_token_id": null,
|
296 |
+
"forced_eos_token_id": null,
|
297 |
+
"fullatt_block_indexes": [
|
298 |
+
7,
|
299 |
+
15,
|
300 |
+
23,
|
301 |
+
31
|
302 |
+
],
|
303 |
+
"hidden_act": "silu",
|
304 |
+
"hidden_size": 1280,
|
305 |
+
"id2label": {
|
306 |
+
"0": "LABEL_0",
|
307 |
+
"1": "LABEL_1"
|
308 |
+
},
|
309 |
+
"in_channels": 3,
|
310 |
+
"in_chans": 3,
|
311 |
+
"init_std": 0.02,
|
312 |
+
"intermediate_size": 3420,
|
313 |
+
"is_decoder": false,
|
314 |
+
"is_encoder_decoder": false,
|
315 |
+
"label2id": {
|
316 |
+
"LABEL_0": 0,
|
317 |
+
"LABEL_1": 1
|
318 |
+
},
|
319 |
+
"length_penalty": 1.0,
|
320 |
+
"max_length": 20,
|
321 |
+
"min_length": 0,
|
322 |
+
"model_type": "qwen2_5_omni_vision_encoder",
|
323 |
+
"no_repeat_ngram_size": 0,
|
324 |
+
"num_beam_groups": 1,
|
325 |
+
"num_beams": 1,
|
326 |
+
"num_heads": 16,
|
327 |
+
"num_return_sequences": 1,
|
328 |
+
"out_hidden_size": 3584,
|
329 |
+
"output_attentions": false,
|
330 |
+
"output_hidden_states": false,
|
331 |
+
"output_scores": false,
|
332 |
+
"pad_token_id": null,
|
333 |
+
"patch_size": 14,
|
334 |
+
"prefix": null,
|
335 |
+
"problem_type": null,
|
336 |
+
"pruned_heads": {},
|
337 |
+
"remove_invalid_values": false,
|
338 |
+
"repetition_penalty": 1.0,
|
339 |
+
"return_dict": true,
|
340 |
+
"return_dict_in_generate": false,
|
341 |
+
"sep_token_id": null,
|
342 |
+
"spatial_merge_size": 2,
|
343 |
+
"spatial_patch_size": 14,
|
344 |
+
"suppress_tokens": null,
|
345 |
+
"task_specific_params": null,
|
346 |
+
"temperature": 1.0,
|
347 |
+
"temporal_patch_size": 2,
|
348 |
+
"tf_legacy_loss": false,
|
349 |
+
"tie_encoder_decoder": false,
|
350 |
+
"tie_word_embeddings": true,
|
351 |
+
"tokenizer_class": null,
|
352 |
+
"tokens_per_second": 25,
|
353 |
+
"top_k": 50,
|
354 |
+
"top_p": 1.0,
|
355 |
+
"torch_dtype": null,
|
356 |
+
"torchscript": false,
|
357 |
+
"typical_p": 1.0,
|
358 |
+
"use_bfloat16": false,
|
359 |
+
"window_size": 112
|
360 |
+
},
|
361 |
+
"vision_end_token_id": 151653,
|
362 |
+
"vision_start_token_id": 151652,
|
363 |
+
"vision_token_id": 151654
|
364 |
+
},
|
365 |
+
"token2wav_config": {
|
366 |
+
"_attn_implementation_autoset": true,
|
367 |
+
"bigvgan_config": {
|
368 |
+
"_attn_implementation_autoset": true,
|
369 |
+
"_name_or_path": "",
|
370 |
+
"add_cross_attention": false,
|
371 |
+
"architectures": null,
|
372 |
+
"bad_words_ids": null,
|
373 |
+
"begin_suppress_tokens": null,
|
374 |
+
"bos_token_id": null,
|
375 |
+
"chunk_size_feed_forward": 0,
|
376 |
+
"cross_attention_hidden_size": null,
|
377 |
+
"decoder_start_token_id": null,
|
378 |
+
"diversity_penalty": 0.0,
|
379 |
+
"do_sample": false,
|
380 |
+
"early_stopping": false,
|
381 |
+
"encoder_no_repeat_ngram_size": 0,
|
382 |
+
"eos_token_id": null,
|
383 |
+
"exponential_decay_length_penalty": null,
|
384 |
+
"finetuning_task": null,
|
385 |
+
"forced_bos_token_id": null,
|
386 |
+
"forced_eos_token_id": null,
|
387 |
+
"id2label": {
|
388 |
+
"0": "LABEL_0",
|
389 |
+
"1": "LABEL_1"
|
390 |
+
},
|
391 |
+
"is_decoder": false,
|
392 |
+
"is_encoder_decoder": false,
|
393 |
+
"label2id": {
|
394 |
+
"LABEL_0": 0,
|
395 |
+
"LABEL_1": 1
|
396 |
+
},
|
397 |
+
"length_penalty": 1.0,
|
398 |
+
"max_length": 20,
|
399 |
+
"mel_dim": 80,
|
400 |
+
"min_length": 0,
|
401 |
+
"model_type": "qwen2_5_omni_bigvgan",
|
402 |
+
"no_repeat_ngram_size": 0,
|
403 |
+
"num_beam_groups": 1,
|
404 |
+
"num_beams": 1,
|
405 |
+
"num_return_sequences": 1,
|
406 |
+
"output_attentions": false,
|
407 |
+
"output_hidden_states": false,
|
408 |
+
"output_scores": false,
|
409 |
+
"pad_token_id": null,
|
410 |
+
"prefix": null,
|
411 |
+
"problem_type": null,
|
412 |
+
"pruned_heads": {},
|
413 |
+
"remove_invalid_values": false,
|
414 |
+
"repetition_penalty": 1.0,
|
415 |
+
"resblock_dilation_sizes": [
|
416 |
+
[
|
417 |
+
1,
|
418 |
+
3,
|
419 |
+
5
|
420 |
+
],
|
421 |
+
[
|
422 |
+
1,
|
423 |
+
3,
|
424 |
+
5
|
425 |
+
],
|
426 |
+
[
|
427 |
+
1,
|
428 |
+
3,
|
429 |
+
5
|
430 |
+
]
|
431 |
+
],
|
432 |
+
"resblock_kernel_sizes": [
|
433 |
+
3,
|
434 |
+
7,
|
435 |
+
11
|
436 |
+
],
|
437 |
+
"return_dict": true,
|
438 |
+
"return_dict_in_generate": false,
|
439 |
+
"sep_token_id": null,
|
440 |
+
"suppress_tokens": null,
|
441 |
+
"task_specific_params": null,
|
442 |
+
"temperature": 1.0,
|
443 |
+
"tf_legacy_loss": false,
|
444 |
+
"tie_encoder_decoder": false,
|
445 |
+
"tie_word_embeddings": true,
|
446 |
+
"tokenizer_class": null,
|
447 |
+
"top_k": 50,
|
448 |
+
"top_p": 1.0,
|
449 |
+
"torch_dtype": null,
|
450 |
+
"torchscript": false,
|
451 |
+
"typical_p": 1.0,
|
452 |
+
"upsample_initial_channel": 1536,
|
453 |
+
"upsample_kernel_sizes": [
|
454 |
+
11,
|
455 |
+
7,
|
456 |
+
4,
|
457 |
+
4,
|
458 |
+
4,
|
459 |
+
4
|
460 |
+
],
|
461 |
+
"upsample_rates": [
|
462 |
+
5,
|
463 |
+
3,
|
464 |
+
2,
|
465 |
+
2,
|
466 |
+
2,
|
467 |
+
2
|
468 |
+
],
|
469 |
+
"use_bfloat16": false,
|
470 |
+
"use_bias_at_final": false
|
471 |
+
},
|
472 |
+
"dit_config": {
|
473 |
+
"_attn_implementation_autoset": true,
|
474 |
+
"_name_or_path": "",
|
475 |
+
"add_cross_attention": false,
|
476 |
+
"architectures": null,
|
477 |
+
"bad_words_ids": null,
|
478 |
+
"begin_suppress_tokens": null,
|
479 |
+
"block_size": 24,
|
480 |
+
"bos_token_id": null,
|
481 |
+
"chunk_size_feed_forward": 0,
|
482 |
+
"cross_attention_hidden_size": null,
|
483 |
+
"decoder_start_token_id": null,
|
484 |
+
"depth": 22,
|
485 |
+
"dim": 1024,
|
486 |
+
"diversity_penalty": 0.0,
|
487 |
+
"do_sample": false,
|
488 |
+
"dropout": 0.1,
|
489 |
+
"early_stopping": false,
|
490 |
+
"emb_dim": 512,
|
491 |
+
"enc_attention_channels": 64,
|
492 |
+
"enc_channels": [
|
493 |
+
256,
|
494 |
+
256,
|
495 |
+
256,
|
496 |
+
256,
|
497 |
+
768
|
498 |
+
],
|
499 |
+
"enc_dilations": [
|
500 |
+
1,
|
501 |
+
2,
|
502 |
+
3,
|
503 |
+
4,
|
504 |
+
1
|
505 |
+
],
|
506 |
+
"enc_dim": 128,
|
507 |
+
"enc_emb_dim": 192,
|
508 |
+
"enc_global_context": true,
|
509 |
+
"enc_kernel_sizes": [
|
510 |
+
5,
|
511 |
+
3,
|
512 |
+
3,
|
513 |
+
3,
|
514 |
+
1
|
515 |
+
],
|
516 |
+
"enc_lin_neurons": 192,
|
517 |
+
"enc_res2net_scale": 2,
|
518 |
+
"enc_se_channels": 64,
|
519 |
+
"encoder_no_repeat_ngram_size": 0,
|
520 |
+
"eos_token_id": null,
|
521 |
+
"exponential_decay_length_penalty": null,
|
522 |
+
"ff_mult": 2,
|
523 |
+
"finetuning_task": null,
|
524 |
+
"forced_bos_token_id": null,
|
525 |
+
"forced_eos_token_id": null,
|
526 |
+
"head_dim": 64,
|
527 |
+
"heads": 16,
|
528 |
+
"hidden_size": 1024,
|
529 |
+
"id2label": {
|
530 |
+
"0": "LABEL_0",
|
531 |
+
"1": "LABEL_1"
|
532 |
+
},
|
533 |
+
"is_decoder": false,
|
534 |
+
"is_encoder_decoder": false,
|
535 |
+
"label2id": {
|
536 |
+
"LABEL_0": 0,
|
537 |
+
"LABEL_1": 1
|
538 |
+
},
|
539 |
+
"length_penalty": 1.0,
|
540 |
+
"look_ahead_layers": [
|
541 |
+
10
|
542 |
+
],
|
543 |
+
"look_backward_layers": [
|
544 |
+
0,
|
545 |
+
20
|
546 |
+
],
|
547 |
+
"max_length": 20,
|
548 |
+
"max_position_embeddings": 32768,
|
549 |
+
"mel_dim": 80,
|
550 |
+
"min_length": 0,
|
551 |
+
"model_type": "qwen2_5_omni_dit",
|
552 |
+
"no_repeat_ngram_size": 0,
|
553 |
+
"num_attention_heads": 16,
|
554 |
+
"num_beam_groups": 1,
|
555 |
+
"num_beams": 1,
|
556 |
+
"num_embeds": 8193,
|
557 |
+
"num_hidden_layers": 22,
|
558 |
+
"num_return_sequences": 1,
|
559 |
+
"output_attentions": false,
|
560 |
+
"output_hidden_states": false,
|
561 |
+
"output_scores": false,
|
562 |
+
"pad_token_id": null,
|
563 |
+
"prefix": null,
|
564 |
+
"problem_type": null,
|
565 |
+
"pruned_heads": {},
|
566 |
+
"remove_invalid_values": false,
|
567 |
+
"repeats": 2,
|
568 |
+
"repetition_penalty": 1.0,
|
569 |
+
"return_dict": true,
|
570 |
+
"return_dict_in_generate": false,
|
571 |
+
"rope_theta": 10000.0,
|
572 |
+
"sep_token_id": null,
|
573 |
+
"suppress_tokens": null,
|
574 |
+
"task_specific_params": null,
|
575 |
+
"temperature": 1.0,
|
576 |
+
"tf_legacy_loss": false,
|
577 |
+
"tie_encoder_decoder": false,
|
578 |
+
"tie_word_embeddings": true,
|
579 |
+
"tokenizer_class": null,
|
580 |
+
"top_k": 50,
|
581 |
+
"top_p": 1.0,
|
582 |
+
"torch_dtype": "float32",
|
583 |
+
"torchscript": false,
|
584 |
+
"typical_p": 1.0,
|
585 |
+
"use_bfloat16": false
|
586 |
+
},
|
587 |
+
"model_type": "qwen2_5_omni_token2wav",
|
588 |
+
"torch_dtype": "float16"
|
589 |
+
},
|
590 |
+
"torch_dtype": "float16",
|
591 |
+
"transformers_version": "4.50.0.dev0",
|
592 |
+
"use_cache": false
|
593 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.50.0.dev0"
|
4 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f04a51ab40fc364c02855ec5a76bb680be239d04a6314b8f625ae1d0f8306f46
|
3 |
+
size 3980359152
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4690ab05b3edd91cc497017a226bf89383862b8042a10d520a647d0c325456eb
|
3 |
+
size 3137548688
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddca06aa8c99fccc2e54df60360e9328617d448ccf1901bbeb065eac78906d37
|
3 |
+
size 3993379832
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33733bedd858bb3157d479eaba1388693f29b83a26e650810581f33eb1d1c79
|
3 |
+
size 1595686480
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quant_log.csv
ADDED
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
layer,module,loss,samples,damp,time
|
2 |
+
0,self_attn.k_proj,0.84503669,0.01000,0.847
|
3 |
+
0,self_attn.v_proj,0.09790013,0.01000,0.621
|
4 |
+
0,self_attn.q_proj,3.45275998,0.01000,0.623
|
5 |
+
0,self_attn.o_proj,0.02797472,0.01000,0.716
|
6 |
+
0,mlp.up_proj,6.59510899,0.01000,0.753
|
7 |
+
0,mlp.gate_proj,14.64342403,0.01000,0.634
|
8 |
+
0,mlp.down_proj,0.54082263,0.01000,4.907
|
9 |
+
1,self_attn.k_proj,0.66450667,0.01000,0.755
|
10 |
+
1,self_attn.v_proj,0.13586605,0.01000,0.624
|
11 |
+
1,self_attn.q_proj,2.53379679,0.01000,0.622
|
12 |
+
1,self_attn.o_proj,0.01710801,0.01000,0.720
|
13 |
+
1,mlp.up_proj,56.40869904,0.01000,0.752
|
14 |
+
1,mlp.gate_proj,94.36625671,0.01000,0.638
|
15 |
+
1,mlp.down_proj,0.48488298,0.01000,4.885
|
16 |
+
2,self_attn.k_proj,1.85023427,0.01000,0.758
|
17 |
+
2,self_attn.v_proj,0.29796562,0.01000,0.620
|
18 |
+
2,self_attn.q_proj,6.63527250,0.01000,0.624
|
19 |
+
2,self_attn.o_proj,0.05357596,0.01000,0.721
|
20 |
+
2,mlp.up_proj,72.35107422,0.01000,0.754
|
21 |
+
2,mlp.gate_proj,120.69715118,0.01000,0.637
|
22 |
+
2,mlp.down_proj,0.71529531,0.01000,4.897
|
23 |
+
3,self_attn.k_proj,1.83869004,0.01000,0.816
|
24 |
+
3,self_attn.v_proj,0.42401373,0.01000,0.667
|
25 |
+
3,self_attn.q_proj,6.90928888,0.01000,0.638
|
26 |
+
3,self_attn.o_proj,0.22543210,0.01000,0.795
|
27 |
+
3,mlp.up_proj,199.29341125,0.01000,0.756
|
28 |
+
3,mlp.gate_proj,270.88391113,0.01000,0.641
|
29 |
+
3,mlp.down_proj,1.02437985,0.01000,4.892
|
30 |
+
4,self_attn.k_proj,3.05090141,0.01000,0.757
|
31 |
+
4,self_attn.v_proj,0.90732384,0.01000,0.623
|
32 |
+
4,self_attn.q_proj,12.91889858,0.01000,0.622
|
33 |
+
4,self_attn.o_proj,0.16272199,0.01000,0.724
|
34 |
+
4,mlp.up_proj,177.98535156,0.01000,0.751
|
35 |
+
4,mlp.gate_proj,268.20730591,0.01000,0.635
|
36 |
+
4,mlp.down_proj,1.51549566,0.01000,4.892
|
37 |
+
5,self_attn.k_proj,3.06540680,0.01000,0.769
|
38 |
+
5,self_attn.v_proj,1.12325358,0.01000,0.625
|
39 |
+
5,self_attn.q_proj,14.62543392,0.01000,0.622
|
40 |
+
5,self_attn.o_proj,0.21586980,0.01000,0.719
|
41 |
+
5,mlp.up_proj,267.72155762,0.01000,0.769
|
42 |
+
5,mlp.gate_proj,343.41455078,0.01000,0.638
|
43 |
+
5,mlp.down_proj,1.18007314,0.01000,4.889
|
44 |
+
6,self_attn.k_proj,2.07387280,0.01000,0.755
|
45 |
+
6,self_attn.v_proj,0.94506907,0.01000,0.621
|
46 |
+
6,self_attn.q_proj,9.86525154,0.01000,0.625
|
47 |
+
6,self_attn.o_proj,0.26159465,0.01000,0.720
|
48 |
+
6,mlp.up_proj,66.96002197,0.01000,0.760
|
49 |
+
6,mlp.gate_proj,95.20739746,0.01000,0.634
|
50 |
+
6,mlp.down_proj,3.78148937,0.01000,4.891
|
51 |
+
7,self_attn.k_proj,2.32142448,0.01000,0.754
|
52 |
+
7,self_attn.v_proj,1.96631455,0.01000,0.621
|
53 |
+
7,self_attn.q_proj,12.40788651,0.01000,0.621
|
54 |
+
7,self_attn.o_proj,0.92824316,0.01000,0.718
|
55 |
+
7,mlp.up_proj,66.62113190,0.01000,0.756
|
56 |
+
7,mlp.gate_proj,74.05113220,0.01000,0.640
|
57 |
+
7,mlp.down_proj,6.63149881,0.01000,4.882
|
58 |
+
8,self_attn.k_proj,4.55058146,0.01000,0.755
|
59 |
+
8,self_attn.v_proj,1.65348577,0.01000,0.632
|
60 |
+
8,self_attn.q_proj,18.91058159,0.01000,0.649
|
61 |
+
8,self_attn.o_proj,1.66989470,0.01000,0.720
|
62 |
+
8,mlp.up_proj,79.65923309,0.01000,0.748
|
63 |
+
8,mlp.gate_proj,83.44503021,0.01000,0.634
|
64 |
+
8,mlp.down_proj,7.66813326,0.01000,4.916
|
65 |
+
9,self_attn.k_proj,3.84148502,0.01000,0.754
|
66 |
+
9,self_attn.v_proj,2.96535730,0.01000,0.622
|
67 |
+
9,self_attn.q_proj,20.20914268,0.01000,0.626
|
68 |
+
9,self_attn.o_proj,2.59902573,0.01000,0.719
|
69 |
+
9,mlp.up_proj,156.97390747,0.01000,0.753
|
70 |
+
9,mlp.gate_proj,251.82458496,0.01000,0.638
|
71 |
+
9,mlp.down_proj,8.60938835,0.01000,4.885
|
72 |
+
10,self_attn.k_proj,4.07611465,0.01000,0.755
|
73 |
+
10,self_attn.v_proj,2.05425596,0.01000,0.622
|
74 |
+
10,self_attn.q_proj,19.85713577,0.01000,0.623
|
75 |
+
10,self_attn.o_proj,1.43030739,0.01000,0.720
|
76 |
+
10,mlp.up_proj,100.09529114,0.01000,0.749
|
77 |
+
10,mlp.gate_proj,113.80771637,0.01000,0.640
|
78 |
+
10,mlp.down_proj,8.42348957,0.01000,4.895
|
79 |
+
11,self_attn.k_proj,5.21213436,0.01000,0.755
|
80 |
+
11,self_attn.v_proj,1.78169560,0.01000,0.624
|
81 |
+
11,self_attn.q_proj,21.62147522,0.01000,0.625
|
82 |
+
11,self_attn.o_proj,2.29331183,0.01000,0.719
|
83 |
+
11,mlp.up_proj,95.10997009,0.01000,0.754
|
84 |
+
11,mlp.gate_proj,100.02523804,0.01000,0.638
|
85 |
+
11,mlp.down_proj,8.73736763,0.01000,4.897
|
86 |
+
12,self_attn.k_proj,5.94782352,0.01000,0.752
|
87 |
+
12,self_attn.v_proj,2.57430744,0.01000,0.623
|
88 |
+
12,self_attn.q_proj,25.37301826,0.01000,0.624
|
89 |
+
12,self_attn.o_proj,2.74405336,0.01000,0.720
|
90 |
+
12,mlp.up_proj,99.41949463,0.01000,0.760
|
91 |
+
12,mlp.gate_proj,98.57714081,0.01000,0.635
|
92 |
+
12,mlp.down_proj,10.31996155,0.01000,4.876
|
93 |
+
13,self_attn.k_proj,5.70451880,0.01000,0.753
|
94 |
+
13,self_attn.v_proj,3.61313081,0.01000,0.620
|
95 |
+
13,self_attn.q_proj,28.92498398,0.01000,0.623
|
96 |
+
13,self_attn.o_proj,5.05193090,0.01000,0.717
|
97 |
+
13,mlp.up_proj,102.82405853,0.01000,0.753
|
98 |
+
13,mlp.gate_proj,109.35607910,0.01000,0.674
|
99 |
+
13,mlp.down_proj,10.62277031,0.01000,4.872
|
100 |
+
14,self_attn.k_proj,8.16368103,0.01000,0.750
|
101 |
+
14,self_attn.v_proj,3.29415512,0.01000,0.616
|
102 |
+
14,self_attn.q_proj,40.57175064,0.01000,0.618
|
103 |
+
14,self_attn.o_proj,3.70151019,0.01000,0.719
|
104 |
+
14,mlp.up_proj,116.39168549,0.01000,0.752
|
105 |
+
14,mlp.gate_proj,117.40150452,0.01000,0.637
|
106 |
+
14,mlp.down_proj,12.35162067,0.01000,4.897
|
107 |
+
15,self_attn.k_proj,7.40435266,0.01000,0.754
|
108 |
+
15,self_attn.v_proj,2.82182503,0.01000,0.629
|
109 |
+
15,self_attn.q_proj,32.03612518,0.01000,0.622
|
110 |
+
15,self_attn.o_proj,2.86537886,0.01000,0.720
|
111 |
+
15,mlp.up_proj,109.34799194,0.01000,0.816
|
112 |
+
15,mlp.gate_proj,106.16775513,0.01000,0.652
|
113 |
+
15,mlp.down_proj,11.65571213,0.01000,4.899
|
114 |
+
16,self_attn.k_proj,7.20972252,0.01000,0.750
|
115 |
+
16,self_attn.v_proj,3.81571937,0.01000,0.615
|
116 |
+
16,self_attn.q_proj,35.60685730,0.01000,0.617
|
117 |
+
16,self_attn.o_proj,4.76396894,0.01000,0.718
|
118 |
+
16,mlp.up_proj,119.07849121,0.01000,0.753
|
119 |
+
16,mlp.gate_proj,115.41696167,0.01000,0.654
|
120 |
+
16,mlp.down_proj,13.42798615,0.01000,4.888
|
121 |
+
17,self_attn.k_proj,7.86328506,0.01000,0.756
|
122 |
+
17,self_attn.v_proj,4.99391937,0.01000,0.622
|
123 |
+
17,self_attn.q_proj,41.75648499,0.01000,0.624
|
124 |
+
17,self_attn.o_proj,3.45894480,0.01000,0.719
|
125 |
+
17,mlp.up_proj,143.43394470,0.01000,0.754
|
126 |
+
17,mlp.gate_proj,136.14013672,0.01000,0.643
|
127 |
+
17,mlp.down_proj,17.81203842,0.01000,4.882
|
128 |
+
18,self_attn.k_proj,6.22359562,0.01000,0.753
|
129 |
+
18,self_attn.v_proj,6.02423716,0.01000,0.624
|
130 |
+
18,self_attn.q_proj,35.44544601,0.01000,0.624
|
131 |
+
18,self_attn.o_proj,4.30885458,0.01000,0.722
|
132 |
+
18,mlp.up_proj,153.58898926,0.01000,0.760
|
133 |
+
18,mlp.gate_proj,142.47561646,0.01000,0.637
|
134 |
+
18,mlp.down_proj,18.25153732,0.01000,4.894
|
135 |
+
19,self_attn.k_proj,5.90289783,0.01000,0.757
|
136 |
+
19,self_attn.v_proj,6.39343739,0.01000,0.623
|
137 |
+
19,self_attn.q_proj,38.50756073,0.01000,0.624
|
138 |
+
19,self_attn.o_proj,5.47891045,0.01000,0.719
|
139 |
+
19,mlp.up_proj,163.33058167,0.01000,0.758
|
140 |
+
19,mlp.gate_proj,157.55880737,0.01000,0.635
|
141 |
+
19,mlp.down_proj,19.15095139,0.01000,4.872
|
142 |
+
20,self_attn.k_proj,6.11784792,0.01000,0.756
|
143 |
+
20,self_attn.v_proj,7.04739285,0.01000,0.625
|
144 |
+
20,self_attn.q_proj,36.47023392,0.01000,0.623
|
145 |
+
20,self_attn.o_proj,2.35553312,0.01000,0.717
|
146 |
+
20,mlp.up_proj,198.99542236,0.01000,0.750
|
147 |
+
20,mlp.gate_proj,190.01835632,0.01000,0.637
|
148 |
+
20,mlp.down_proj,32.01580811,0.01000,4.894
|
149 |
+
21,self_attn.k_proj,6.29537106,0.01000,0.758
|
150 |
+
21,self_attn.v_proj,10.25707436,0.01000,0.621
|
151 |
+
21,self_attn.q_proj,41.46713257,0.01000,0.621
|
152 |
+
21,self_attn.o_proj,8.36542606,0.01000,0.720
|
153 |
+
21,mlp.up_proj,250.49508667,0.01000,0.751
|
154 |
+
21,mlp.gate_proj,251.44859314,0.01000,0.636
|
155 |
+
21,mlp.down_proj,43.56330109,0.01000,4.881
|
156 |
+
22,self_attn.k_proj,8.49018574,0.01000,0.758
|
157 |
+
22,self_attn.v_proj,17.15532875,0.01000,0.622
|
158 |
+
22,self_attn.q_proj,56.59531021,0.01000,0.622
|
159 |
+
22,self_attn.o_proj,3.68090487,0.01000,0.717
|
160 |
+
22,mlp.up_proj,337.93640137,0.01000,0.756
|
161 |
+
22,mlp.gate_proj,333.52142334,0.01000,0.632
|
162 |
+
22,mlp.down_proj,67.46343994,0.01000,4.917
|
163 |
+
23,self_attn.k_proj,12.21148396,0.01000,0.757
|
164 |
+
23,self_attn.v_proj,25.81269073,0.01000,0.621
|
165 |
+
23,self_attn.q_proj,71.46172333,0.01000,0.623
|
166 |
+
23,self_attn.o_proj,11.98000240,0.01000,0.720
|
167 |
+
23,mlp.up_proj,483.65325928,0.01000,0.752
|
168 |
+
23,mlp.gate_proj,493.06561279,0.01000,0.635
|
169 |
+
23,mlp.down_proj,85.32797241,0.01000,4.916
|
170 |
+
24,self_attn.k_proj,9.50092220,0.01000,0.755
|
171 |
+
24,self_attn.v_proj,26.38395882,0.01000,0.623
|
172 |
+
24,self_attn.q_proj,66.23488617,0.01000,0.624
|
173 |
+
24,self_attn.o_proj,8.46130848,0.01000,0.730
|
174 |
+
24,mlp.up_proj,575.74047852,0.01000,0.748
|
175 |
+
24,mlp.gate_proj,538.54052734,0.01000,0.636
|
176 |
+
24,mlp.down_proj,111.23144531,0.01000,4.899
|
177 |
+
25,self_attn.k_proj,11.69873905,0.01000,0.754
|
178 |
+
25,self_attn.v_proj,50.58491135,0.01000,0.623
|
179 |
+
25,self_attn.q_proj,81.08997345,0.01000,0.622
|
180 |
+
25,self_attn.o_proj,11.35678291,0.01000,0.721
|
181 |
+
25,mlp.up_proj,770.88513184,0.01000,0.761
|
182 |
+
25,mlp.gate_proj,682.92773438,0.01000,0.637
|
183 |
+
25,mlp.down_proj,195.86593628,0.01000,4.877
|
184 |
+
26,self_attn.k_proj,15.98041534,0.01000,0.748
|
185 |
+
26,self_attn.v_proj,117.35370636,0.01000,0.618
|
186 |
+
26,self_attn.q_proj,119.34364319,0.01000,0.628
|
187 |
+
26,self_attn.o_proj,26.08083153,0.01000,0.716
|
188 |
+
26,mlp.up_proj,769.50878906,0.01000,0.747
|
189 |
+
26,mlp.gate_proj,671.80041504,0.01000,0.633
|
190 |
+
26,mlp.down_proj,279.47283936,0.01000,4.886
|
191 |
+
27,self_attn.k_proj,19.93762970,0.01000,0.750
|
192 |
+
27,self_attn.v_proj,191.60113525,0.01000,0.616
|
193 |
+
27,self_attn.q_proj,190.72473145,0.01000,0.619
|
194 |
+
27,self_attn.o_proj,32.69224930,0.01000,0.715
|
195 |
+
27,mlp.up_proj,870.30517578,0.01000,0.751
|
196 |
+
27,mlp.gate_proj,839.04919434,0.01000,0.634
|
197 |
+
27,mlp.down_proj,378.88079834,0.01000,4.875
|
quantize_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"desc_act": true,
|
5 |
+
"sym": true,
|
6 |
+
"lm_head": false,
|
7 |
+
"quant_method": "gptq",
|
8 |
+
"checkpoint_format": "gptq",
|
9 |
+
"pack_dtype": "int32",
|
10 |
+
"meta": {
|
11 |
+
"quantizer": [
|
12 |
+
"gptqmodel:2.1.1-dev"
|
13 |
+
],
|
14 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
15 |
+
"damp_percent": 0.01,
|
16 |
+
"damp_auto_increment": 0.0025,
|
17 |
+
"static_groups": false,
|
18 |
+
"true_sequential": true,
|
19 |
+
"mse": 0.0
|
20 |
+
}
|
21 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|AUDIO|>",
|
6 |
+
"<|audio_bos|>",
|
7 |
+
"<|audio_eos|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_bos|>",
|
12 |
+
"<|vision_eos|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|IMAGE|>",
|
15 |
+
"<|VIDEO|>"
|
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": "<unk>"
|
25 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
|
3 |
+
size 11421870
|
tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|AUDIO|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|audio_bos|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|audio_eos|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|box_end|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|quad_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|quad_end|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|vision_bos|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|vision_eos|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|vision_pad|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|IMAGE|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|VIDEO|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"151657": {
|
117 |
+
"content": "<tool_call>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"151658": {
|
125 |
+
"content": "</tool_call>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"151659": {
|
133 |
+
"content": "<|fim_prefix|>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"151660": {
|
141 |
+
"content": "<|fim_middle|>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"151661": {
|
149 |
+
"content": "<|fim_suffix|>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"151662": {
|
157 |
+
"content": "<|fim_pad|>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"151663": {
|
165 |
+
"content": "<|repo_name|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"151664": {
|
173 |
+
"content": "<|file_sep|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
}
|
180 |
+
},
|
181 |
+
"additional_special_tokens": [
|
182 |
+
"<|im_start|>",
|
183 |
+
"<|im_end|>",
|
184 |
+
"<|AUDIO|>",
|
185 |
+
"<|audio_bos|>",
|
186 |
+
"<|audio_eos|>",
|
187 |
+
"<|box_end|>",
|
188 |
+
"<|quad_start|>",
|
189 |
+
"<|quad_end|>",
|
190 |
+
"<|vision_bos|>",
|
191 |
+
"<|vision_eos|>",
|
192 |
+
"<|vision_pad|>",
|
193 |
+
"<|IMAGE|>",
|
194 |
+
"<|VIDEO|>"
|
195 |
+
],
|
196 |
+
"bos_token": null,
|
197 |
+
"chat_template": "{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
198 |
+
"clean_up_tokenization_spaces": false,
|
199 |
+
"eos_token": "<|im_end|>",
|
200 |
+
"errors": "replace",
|
201 |
+
"extra_special_tokens": {},
|
202 |
+
"model_max_length": 32768,
|
203 |
+
"pad_token": "<unk>",
|
204 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
205 |
+
"split_special_tokens": false,
|
206 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
207 |
+
"unk_token": null,
|
208 |
+
"_commit_hash": null
|
209 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|