kcz358 commited on
Commit
798c0f7
·
verified ·
1 Parent(s): eb8afe1

Add files using upload-large-folder tool

Browse files
.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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<image>": 151665,
4
+ "<tool_call>": 151657,
5
+ "<video>": 151666,
6
+ "<|AUDIO|>": 151667,
7
+ "<|box_end|>": 151649,
8
+ "<|box_start|>": 151648,
9
+ "<|endoftext|>": 151643,
10
+ "<|file_sep|>": 151664,
11
+ "<|fim_middle|>": 151660,
12
+ "<|fim_pad|>": 151662,
13
+ "<|fim_prefix|>": 151659,
14
+ "<|fim_suffix|>": 151661,
15
+ "<|im_end|>": 151645,
16
+ "<|im_start|>": 151644,
17
+ "<|image_pad|>": 151655,
18
+ "<|object_ref_end|>": 151647,
19
+ "<|object_ref_start|>": 151646,
20
+ "<|quad_end|>": 151651,
21
+ "<|quad_start|>": 151650,
22
+ "<|repo_name|>": 151663,
23
+ "<|video_pad|>": 151656,
24
+ "<|vision_end|>": 151653,
25
+ "<|vision_pad|>": 151654,
26
+ "<|vision_start|>": 151652
27
+ }
chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% set audio_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}<|AUDIO|>
6
+ {% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
7
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
8
+ {% endif %}
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AeroForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "_attn_implementation_autoset": true,
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "attention_dropout": 0.0,
10
+ "d_model": 1280,
11
+ "dropout": 0.0,
12
+ "encoder_attention_heads": 20,
13
+ "encoder_ffn_dim": 5120,
14
+ "encoder_layerdrop": 0.0,
15
+ "encoder_layers": 32,
16
+ "init_std": 0.02,
17
+ "initializer_range": 0.02,
18
+ "max_source_positions": 1500,
19
+ "model_type": "qwen2_audio_encoder",
20
+ "num_hidden_layers": 32,
21
+ "num_mel_bins": 128,
22
+ "scale_embedding": false,
23
+ "torch_dtype": "bfloat16"
24
+ },
25
+ "audio_token_index": 151667,
26
+ "model_type": "aero",
27
+ "text_config": {
28
+ "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
29
+ "architectures": [
30
+ "Qwen2ForCausalLM"
31
+ ],
32
+ "attention_dropout": 0.0,
33
+ "bos_token_id": 151643,
34
+ "eos_token_id": 151645,
35
+ "hidden_act": "silu",
36
+ "hidden_size": 1536,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 8960,
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 21,
41
+ "model_type": "qwen2",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 28,
44
+ "num_key_value_heads": 2,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": 32768,
49
+ "tie_word_embeddings": true,
50
+ "torch_dtype": "bfloat16",
51
+ "use_cache": true,
52
+ "use_sliding_window": false,
53
+ "vocab_size": 152000
54
+ },
55
+ "tie_word_embeddings": false,
56
+ "torch_dtype": "bfloat16",
57
+ "transformers_version": "4.52.0.dev0"
58
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.52.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f481632a9ced2621706a60d1b58dda5c03307c3bf9e963214561f97e837ff1ef
3
+ size 4832542496
preprocessor_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "processor_class": "AeroProcessor",
13
+ "return_attention_mask": true,
14
+ "sampling_rate": 16000
15
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|AUDIO|>",
3
+ "processor_class": "AeroProcessor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8afb48f724f353c073eeb9dcb028d071cf5f8013dd99acdd4a7e9223c0c61bda
3
+ size 11422450
tokenizer_config.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<video>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|AUDIO|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ }
205
+ },
206
+ "additional_special_tokens": [
207
+ "<|im_start|>",
208
+ "<|im_end|>",
209
+ "<|object_ref_start|>",
210
+ "<|object_ref_end|>",
211
+ "<|box_start|>",
212
+ "<|box_end|>",
213
+ "<|quad_start|>",
214
+ "<|quad_end|>",
215
+ "<|vision_start|>",
216
+ "<|vision_end|>",
217
+ "<|vision_pad|>",
218
+ "<|image_pad|>",
219
+ "<|video_pad|>"
220
+ ],
221
+ "bos_token": null,
222
+ "clean_up_tokenization_spaces": false,
223
+ "eos_token": "<|im_end|>",
224
+ "errors": "replace",
225
+ "extra_special_tokens": {},
226
+ "model_max_length": 131072,
227
+ "pad_token": "<|endoftext|>",
228
+ "processor_class": "AeroProcessor",
229
+ "split_special_tokens": false,
230
+ "tokenizer_class": "Qwen2Tokenizer",
231
+ "unk_token": null
232
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff