shenyunhang commited on
Commit
3d255b2
·
1 Parent(s): 99522d2
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/cfs2/lhj/videomllm_ckpt/outputs/vita_video_audio_1021/llava-s2-pretrain_video",
3
+ "architectures": [
4
+ "VITAQwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "freeze_audio_encoder": true,
10
+ "freeze_audio_encoder_adapter": true,
11
+ "freeze_mm_mlp_adapter": false,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3584,
14
+ "image_aspect_ratio": "square",
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 28,
19
+ "mm_audio_encoder": "/mnt/cfs2/lhj/model_weights/audio-encoder-Qwen2-7B-1107-weight-base-11wh-tunning",
20
+ "mm_hidden_size": 4096,
21
+ "mm_projector_lr": 2e-06,
22
+ "mm_projector_type": "mlp2x_gelu",
23
+ "mm_vision_tower": "/mnt/cfs/lhj/model_weights/InternViT-300M-448px",
24
+ "model_type": "vita-Qwen2",
25
+ "num_attention_heads": 28,
26
+ "num_hidden_layers": 28,
27
+ "num_key_value_heads": 4,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": null,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_model_max_length": 6200,
33
+ "tokenizer_padding_side": "right",
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.44.2",
36
+ "tune_audio_mlp_adapter": false,
37
+ "tune_mm_mlp_adapter": false,
38
+ "unfreeze_vision_tower": true,
39
+ "use_cache": true,
40
+ "use_mm_proj": true,
41
+ "use_s2": false,
42
+ "use_sliding_window": false,
43
+ "vocab_size": 152064
44
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.44.2"
15
+ }
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:f3f17a1ef8964a3b8345f8f1bd0dd9b2b9cb1d45e39ff78ff72178c0353be6b4
3
+ size 4877660776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26eff25e0b87a9d27916bb6346226d4a0f591dfacbc43056dfd802546dc270f
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797f6dcfb8c0973c85b226fd4015443bcb4b37fc28633750f9df95468e173ad4
3
+ size 4994021888
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2ae405efc54864dfb2fbf00e2bef3b76babc879b356ea9c677aa85f5d327c8
3
+ size 1841613760
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\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 {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 6200,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vita_tts_ckpt/codec/final.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c04d618827b0e2778280d7c4701d6c8450c4104de4c1a1dca2b5c3120017c7a
3
+ size 253718273
vita_tts_ckpt/codec/model.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "resblock": "1",
3
+ "num_gpus": 8,
4
+ "batch_size": 160,
5
+ "learning_rate": 0.0002,
6
+ "adam_b1": 0.5,
7
+ "adam_b2": 0.9,
8
+ "lr_decay": 0.98,
9
+ "seed": 1234,
10
+
11
+ "upsample_rates": [8,5,5,3],
12
+ "upsample_kernel_sizes": [16,11,11,5],
13
+ "upsample_initial_channel": 512,
14
+ "resblock_kernel_sizes": [3,7,11],
15
+ "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
16
+
17
+ "segment_size": 24000,
18
+ "num_mels": 80,
19
+ "num_freq": 1025,
20
+ "n_fft": 1024,
21
+ "hop_size": 240,
22
+ "win_size": 1024,
23
+
24
+ "sampling_rate": 24000,
25
+
26
+ "n_code_groups": 1,
27
+ "residul_layer": 1,
28
+ "n_codes": 1024,
29
+ "codebook_loss_lambda": 1.0,
30
+ "commitment_loss_lambda": 0.25,
31
+ "global_code_num": 8,
32
+ "global_feature_conv":[128, 64, 128, 3, 1],
33
+ "global_tokens": [473,975,419,219,565,121,550,616],
34
+
35
+ "fmin": 0,
36
+ "fmax": 8000,
37
+ "fmax_for_loss": null,
38
+
39
+ "num_workers": 12
40
+ }
vita_tts_ckpt/decoder/final.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3274da94685758ce37209759ac7542ea8f2d6b47c00d1cc18c051d0d33cc3e
3
+ size 1194900847
vita_tts_ckpt/decoder/model.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ 896,
3
+ 1024,
4
+ {
5
+ "accum_grad": 3,
6
+ "char_list": [],
7
+ "debugmode": 0,
8
+ "encoder_criterion": "ce",
9
+ "encoder_drop_rate": 0.1,
10
+ "encoder_input_dim": 896,
11
+ "encoder_layer_config": "transformer",
12
+ "encoder_output_dim": 896,
13
+ "encoder_pre_norm_type": "ln",
14
+ "encoder_upsample_rate": 9,
15
+ "kv_cache_prefix_finetune": 0,
16
+ "epochs": 100,
17
+ "eps": 1e-08,
18
+ "eps_decay": 0.8,
19
+ "gpu_id": null,
20
+ "gpu_num": 1,
21
+ "grad_clip": 5,
22
+ "grad_noise": false,
23
+ "idim": 896,
24
+ "init_lr": 0.0005,
25
+ "lsm_weight": 0.0,
26
+ "max_batch_size": 25,
27
+ "max_duration": 256,
28
+ "max_mem": 20000,
29
+ "mtlalpha": 0.5,
30
+ "n_iter_processes": 8,
31
+ "noam_warmup_steps": 4000,
32
+ "odim": 1024,
33
+ "opt": "noamw",
34
+ "rank": 0,
35
+ "report_interval_iters": 100,
36
+ "resume_trainer": false,
37
+ "save_interval_iters": 2000,
38
+ "seed": 19832,
39
+ "sort_duration": true,
40
+ "start_decay_epoch": 5,
41
+ "stop_learning_rate": 1e-05,
42
+ "sycn_batchnorm": false,
43
+ "tensorboard_dir": null,
44
+ "train_dtype": "bfloat16",
45
+ "transformer_attention_dim": 896,
46
+ "transformer_attention_dropout_rate": 0.1,
47
+ "transformer_attention_heads": 14,
48
+ "transformer_chunk_size": [
49
+ 1
50
+ ],
51
+ "transformer_concat_after": false,
52
+ "transformer_dropout_rate": 0.1,
53
+ "transformer_dynamic_chunks": false,
54
+ "transformer_input_dim": 896,
55
+ "transformer_input_layer": "linear",
56
+ "transformer_left_chunks": [
57
+ -1
58
+ ],
59
+ "transformer_linear_units": 4864,
60
+ "transformer_normalize_before": true,
61
+ "transformer_num_blocks": 4,
62
+ "transformer_output_dim": 896,
63
+ "transformer_pos_enc_class": "rel-enc",
64
+ "transformer_positional_dropout_rate": 0.1,
65
+ "transformer_positionwise_conv_kernel_size": 1,
66
+ "transformer_positionwise_layer_type": "linear",
67
+ "use_zero_redun_opt": false,
68
+ "verbose": 0,
69
+ "weight_decay": 0.05,
70
+ "world_size": 1
71
+ }
72
+ ]
vocab.json ADDED
The diff for this file is too large to render. See raw diff