Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- config.json +642 -0
- generation_config.json +8 -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
- preprocessor_config.json +31 -0
- special_tokens_map.json +38 -0
- spk_dict.pt +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +222 -0
- video_preprocessor_config.json +57 -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 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% 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
|
| 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 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|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,642 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5OmniForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"enable_audio_output": false,
|
| 7 |
+
"enable_talker": true,
|
| 8 |
+
"hidden_size": 3584,
|
| 9 |
+
"keys_to_ignore_at_inference": [
|
| 10 |
+
"past_key_values",
|
| 11 |
+
"hidden_states",
|
| 12 |
+
"attention_mask",
|
| 13 |
+
"hidden_states",
|
| 14 |
+
"attention_mask",
|
| 15 |
+
"hidden_states",
|
| 16 |
+
"attention_mask",
|
| 17 |
+
"hidden_states",
|
| 18 |
+
"attention_mask"
|
| 19 |
+
],
|
| 20 |
+
"model_type": "qwen2_5_omni",
|
| 21 |
+
"pad_token_id": 151643,
|
| 22 |
+
"talker_config": {
|
| 23 |
+
"_attn_implementation_autoset": true,
|
| 24 |
+
"_name_or_path": "Qwen2.5-Omni-7B/talker",
|
| 25 |
+
"architectures": [
|
| 26 |
+
"Qwen2OmniTalkerForConditionalGeneration"
|
| 27 |
+
],
|
| 28 |
+
"attention_dropout": 0.0,
|
| 29 |
+
"audio_end_token_id": 151648,
|
| 30 |
+
"audio_start_token_id": 151647,
|
| 31 |
+
"audio_token_index": 151646,
|
| 32 |
+
"dtype": "bfloat16",
|
| 33 |
+
"embedding_size": 3584,
|
| 34 |
+
"head_dim": 128,
|
| 35 |
+
"hidden_act": "silu",
|
| 36 |
+
"hidden_size": 896,
|
| 37 |
+
"image_token_index": 151655,
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 18944,
|
| 41 |
+
"layer_types": [
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention"
|
| 66 |
+
],
|
| 67 |
+
"max_position_embeddings": 32768,
|
| 68 |
+
"max_window_layers": 28,
|
| 69 |
+
"model_type": "qwen2_5_omni_talker",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_hidden_layers": 24,
|
| 72 |
+
"num_key_value_heads": 4,
|
| 73 |
+
"position_id_per_seconds": 25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": {
|
| 76 |
+
"mrope_section": [
|
| 77 |
+
16,
|
| 78 |
+
24,
|
| 79 |
+
24
|
| 80 |
+
],
|
| 81 |
+
"rope_type": "default",
|
| 82 |
+
"type": "default"
|
| 83 |
+
},
|
| 84 |
+
"rope_theta": 1000000.0,
|
| 85 |
+
"seconds_per_chunk": 2,
|
| 86 |
+
"sliding_window": null,
|
| 87 |
+
"spatial_merge_size": 2,
|
| 88 |
+
"tts_codec_end_token_id": 8294,
|
| 89 |
+
"tts_codec_mask_token_id": 8296,
|
| 90 |
+
"tts_codec_pad_token_id": 8292,
|
| 91 |
+
"tts_codec_start_token_id": 8293,
|
| 92 |
+
"tts_text_end_token_id": 151861,
|
| 93 |
+
"tts_text_pad_token_id": 151859,
|
| 94 |
+
"tts_text_start_token_id": 151860,
|
| 95 |
+
"use_cache": true,
|
| 96 |
+
"use_sliding_window": false,
|
| 97 |
+
"video_token_index": 151656,
|
| 98 |
+
"vision_end_token_id": 151653,
|
| 99 |
+
"vision_start_token_id": 151652,
|
| 100 |
+
"vocab_size": 8448
|
| 101 |
+
},
|
| 102 |
+
"thinker_config": {
|
| 103 |
+
"_attn_implementation_autoset": true,
|
| 104 |
+
"_name_or_path": "Qwen2.5-Omni-7B/thinker",
|
| 105 |
+
"architectures": [
|
| 106 |
+
"Qwen2OmniNaViTThinkerForConditionalGeneration"
|
| 107 |
+
],
|
| 108 |
+
"audio_config": {
|
| 109 |
+
"_attn_implementation_autoset": true,
|
| 110 |
+
"_name_or_path": "",
|
| 111 |
+
"activation_dropout": 0.0,
|
| 112 |
+
"activation_function": "gelu",
|
| 113 |
+
"add_cross_attention": false,
|
| 114 |
+
"architectures": null,
|
| 115 |
+
"attention_dropout": 0.0,
|
| 116 |
+
"bad_words_ids": null,
|
| 117 |
+
"begin_suppress_tokens": null,
|
| 118 |
+
"bos_token_id": null,
|
| 119 |
+
"chunk_size_feed_forward": 0,
|
| 120 |
+
"cross_attention_hidden_size": null,
|
| 121 |
+
"d_model": 1280,
|
| 122 |
+
"decoder_start_token_id": null,
|
| 123 |
+
"diversity_penalty": 0.0,
|
| 124 |
+
"do_sample": false,
|
| 125 |
+
"dropout": 0.0,
|
| 126 |
+
"dtype": "bfloat16",
|
| 127 |
+
"early_stopping": false,
|
| 128 |
+
"encoder_attention_heads": 20,
|
| 129 |
+
"encoder_ffn_dim": 5120,
|
| 130 |
+
"encoder_layerdrop": 0.0,
|
| 131 |
+
"encoder_layers": 32,
|
| 132 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 133 |
+
"eos_token_id": null,
|
| 134 |
+
"exponential_decay_length_penalty": null,
|
| 135 |
+
"finetuning_task": null,
|
| 136 |
+
"forced_bos_token_id": null,
|
| 137 |
+
"forced_eos_token_id": null,
|
| 138 |
+
"id2label": {
|
| 139 |
+
"0": "LABEL_0",
|
| 140 |
+
"1": "LABEL_1"
|
| 141 |
+
},
|
| 142 |
+
"init_std": 0.02,
|
| 143 |
+
"initializer_range": 0.02,
|
| 144 |
+
"is_decoder": false,
|
| 145 |
+
"is_encoder_decoder": false,
|
| 146 |
+
"label2id": {
|
| 147 |
+
"LABEL_0": 0,
|
| 148 |
+
"LABEL_1": 1
|
| 149 |
+
},
|
| 150 |
+
"length_penalty": 1.0,
|
| 151 |
+
"max_length": 20,
|
| 152 |
+
"max_source_positions": 1500,
|
| 153 |
+
"min_length": 0,
|
| 154 |
+
"model_type": "qwen2_5_omni_audio_encoder",
|
| 155 |
+
"n_window": 100,
|
| 156 |
+
"no_repeat_ngram_size": 0,
|
| 157 |
+
"num_beam_groups": 1,
|
| 158 |
+
"num_beams": 1,
|
| 159 |
+
"num_hidden_layers": 32,
|
| 160 |
+
"num_mel_bins": 128,
|
| 161 |
+
"num_return_sequences": 1,
|
| 162 |
+
"output_attentions": false,
|
| 163 |
+
"output_dim": 3584,
|
| 164 |
+
"output_hidden_states": false,
|
| 165 |
+
"output_scores": false,
|
| 166 |
+
"pad_token_id": 151643,
|
| 167 |
+
"prefix": null,
|
| 168 |
+
"problem_type": null,
|
| 169 |
+
"pruned_heads": {},
|
| 170 |
+
"remove_invalid_values": false,
|
| 171 |
+
"repetition_penalty": 1.0,
|
| 172 |
+
"return_dict": true,
|
| 173 |
+
"return_dict_in_generate": false,
|
| 174 |
+
"scale_embedding": false,
|
| 175 |
+
"sep_token_id": null,
|
| 176 |
+
"suppress_tokens": null,
|
| 177 |
+
"task_specific_params": null,
|
| 178 |
+
"temperature": 1.0,
|
| 179 |
+
"tf_legacy_loss": false,
|
| 180 |
+
"tie_encoder_decoder": false,
|
| 181 |
+
"tie_word_embeddings": true,
|
| 182 |
+
"tokenizer_class": null,
|
| 183 |
+
"top_k": 50,
|
| 184 |
+
"top_p": 1.0,
|
| 185 |
+
"torchscript": false,
|
| 186 |
+
"typical_p": 1.0,
|
| 187 |
+
"use_bfloat16": false
|
| 188 |
+
},
|
| 189 |
+
"audio_end_token_id": 151648,
|
| 190 |
+
"audio_start_token_id": 151647,
|
| 191 |
+
"audio_token_index": 151646,
|
| 192 |
+
"bos_token_id": 151644,
|
| 193 |
+
"dtype": "bfloat16",
|
| 194 |
+
"eos_token_id": 151645,
|
| 195 |
+
"ignore_index": -100,
|
| 196 |
+
"image_token_index": 151655,
|
| 197 |
+
"init_std": 0.02,
|
| 198 |
+
"initializer_range": 0.02,
|
| 199 |
+
"model_type": "qwen2_5_omni_thinker",
|
| 200 |
+
"pad_token_id": 151643,
|
| 201 |
+
"position_id_per_seconds": 25,
|
| 202 |
+
"seconds_per_chunk": 2,
|
| 203 |
+
"text_config": {
|
| 204 |
+
"_name_or_path": "",
|
| 205 |
+
"add_cross_attention": false,
|
| 206 |
+
"architectures": null,
|
| 207 |
+
"attention_dropout": 0.0,
|
| 208 |
+
"bad_words_ids": null,
|
| 209 |
+
"begin_suppress_tokens": null,
|
| 210 |
+
"bos_token_id": null,
|
| 211 |
+
"chunk_size_feed_forward": 0,
|
| 212 |
+
"cross_attention_hidden_size": null,
|
| 213 |
+
"decoder_start_token_id": null,
|
| 214 |
+
"diversity_penalty": 0.0,
|
| 215 |
+
"do_sample": false,
|
| 216 |
+
"dtype": "bfloat16",
|
| 217 |
+
"early_stopping": false,
|
| 218 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 219 |
+
"eos_token_id": null,
|
| 220 |
+
"exponential_decay_length_penalty": null,
|
| 221 |
+
"finetuning_task": null,
|
| 222 |
+
"forced_bos_token_id": null,
|
| 223 |
+
"forced_eos_token_id": null,
|
| 224 |
+
"hidden_act": "silu",
|
| 225 |
+
"hidden_size": 3584,
|
| 226 |
+
"id2label": {
|
| 227 |
+
"0": "LABEL_0",
|
| 228 |
+
"1": "LABEL_1"
|
| 229 |
+
},
|
| 230 |
+
"init_std": 0.02,
|
| 231 |
+
"initializer_range": 0.02,
|
| 232 |
+
"intermediate_size": 18944,
|
| 233 |
+
"is_decoder": false,
|
| 234 |
+
"is_encoder_decoder": false,
|
| 235 |
+
"label2id": {
|
| 236 |
+
"LABEL_0": 0,
|
| 237 |
+
"LABEL_1": 1
|
| 238 |
+
},
|
| 239 |
+
"layer_types": [
|
| 240 |
+
"full_attention",
|
| 241 |
+
"full_attention",
|
| 242 |
+
"full_attention",
|
| 243 |
+
"full_attention",
|
| 244 |
+
"full_attention",
|
| 245 |
+
"full_attention",
|
| 246 |
+
"full_attention",
|
| 247 |
+
"full_attention",
|
| 248 |
+
"full_attention",
|
| 249 |
+
"full_attention",
|
| 250 |
+
"full_attention",
|
| 251 |
+
"full_attention",
|
| 252 |
+
"full_attention",
|
| 253 |
+
"full_attention",
|
| 254 |
+
"full_attention",
|
| 255 |
+
"full_attention",
|
| 256 |
+
"full_attention",
|
| 257 |
+
"full_attention",
|
| 258 |
+
"full_attention",
|
| 259 |
+
"full_attention",
|
| 260 |
+
"full_attention",
|
| 261 |
+
"full_attention",
|
| 262 |
+
"full_attention",
|
| 263 |
+
"full_attention",
|
| 264 |
+
"full_attention",
|
| 265 |
+
"full_attention",
|
| 266 |
+
"full_attention",
|
| 267 |
+
"full_attention"
|
| 268 |
+
],
|
| 269 |
+
"length_penalty": 1.0,
|
| 270 |
+
"max_length": 20,
|
| 271 |
+
"max_position_embeddings": 32768,
|
| 272 |
+
"max_window_layers": 28,
|
| 273 |
+
"min_length": 0,
|
| 274 |
+
"model_type": "qwen2_5_omni_text",
|
| 275 |
+
"no_repeat_ngram_size": 0,
|
| 276 |
+
"num_attention_heads": 28,
|
| 277 |
+
"num_beam_groups": 1,
|
| 278 |
+
"num_beams": 1,
|
| 279 |
+
"num_hidden_layers": 28,
|
| 280 |
+
"num_key_value_heads": 4,
|
| 281 |
+
"num_return_sequences": 1,
|
| 282 |
+
"output_attentions": false,
|
| 283 |
+
"output_hidden_states": false,
|
| 284 |
+
"output_scores": false,
|
| 285 |
+
"pad_token_id": 151643,
|
| 286 |
+
"prefix": null,
|
| 287 |
+
"problem_type": null,
|
| 288 |
+
"pruned_heads": {},
|
| 289 |
+
"remove_invalid_values": false,
|
| 290 |
+
"repetition_penalty": 1.0,
|
| 291 |
+
"return_dict": true,
|
| 292 |
+
"return_dict_in_generate": false,
|
| 293 |
+
"rms_norm_eps": 1e-06,
|
| 294 |
+
"rope_scaling": {
|
| 295 |
+
"mrope_section": [
|
| 296 |
+
16,
|
| 297 |
+
24,
|
| 298 |
+
24
|
| 299 |
+
],
|
| 300 |
+
"rope_type": "default",
|
| 301 |
+
"type": "default"
|
| 302 |
+
},
|
| 303 |
+
"rope_theta": 1000000.0,
|
| 304 |
+
"sep_token_id": null,
|
| 305 |
+
"sliding_window": null,
|
| 306 |
+
"suppress_tokens": null,
|
| 307 |
+
"task_specific_params": null,
|
| 308 |
+
"temperature": 1.0,
|
| 309 |
+
"tf_legacy_loss": false,
|
| 310 |
+
"tie_encoder_decoder": false,
|
| 311 |
+
"tie_word_embeddings": false,
|
| 312 |
+
"tokenizer_class": null,
|
| 313 |
+
"top_k": 50,
|
| 314 |
+
"top_p": 1.0,
|
| 315 |
+
"torchscript": false,
|
| 316 |
+
"typical_p": 1.0,
|
| 317 |
+
"use_bfloat16": false,
|
| 318 |
+
"use_cache": false,
|
| 319 |
+
"use_sliding_window": false,
|
| 320 |
+
"vocab_size": 152064
|
| 321 |
+
},
|
| 322 |
+
"user_token_id": 872,
|
| 323 |
+
"video_token_index": 151656,
|
| 324 |
+
"vision_config": {
|
| 325 |
+
"_attn_implementation_autoset": true,
|
| 326 |
+
"_name_or_path": "",
|
| 327 |
+
"add_cross_attention": false,
|
| 328 |
+
"architectures": null,
|
| 329 |
+
"bad_words_ids": null,
|
| 330 |
+
"begin_suppress_tokens": null,
|
| 331 |
+
"bos_token_id": null,
|
| 332 |
+
"chunk_size_feed_forward": 0,
|
| 333 |
+
"cross_attention_hidden_size": null,
|
| 334 |
+
"decoder_start_token_id": null,
|
| 335 |
+
"depth": 32,
|
| 336 |
+
"diversity_penalty": 0.0,
|
| 337 |
+
"do_sample": false,
|
| 338 |
+
"dtype": "bfloat16",
|
| 339 |
+
"early_stopping": false,
|
| 340 |
+
"embed_dim": 1280,
|
| 341 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 342 |
+
"eos_token_id": null,
|
| 343 |
+
"exponential_decay_length_penalty": null,
|
| 344 |
+
"finetuning_task": null,
|
| 345 |
+
"forced_bos_token_id": null,
|
| 346 |
+
"forced_eos_token_id": null,
|
| 347 |
+
"fullatt_block_indexes": [
|
| 348 |
+
7,
|
| 349 |
+
15,
|
| 350 |
+
23,
|
| 351 |
+
31
|
| 352 |
+
],
|
| 353 |
+
"hidden_act": "silu",
|
| 354 |
+
"hidden_size": 1280,
|
| 355 |
+
"id2label": {
|
| 356 |
+
"0": "LABEL_0",
|
| 357 |
+
"1": "LABEL_1"
|
| 358 |
+
},
|
| 359 |
+
"in_channels": 3,
|
| 360 |
+
"in_chans": 3,
|
| 361 |
+
"init_std": 0.02,
|
| 362 |
+
"initializer_range": 0.02,
|
| 363 |
+
"intermediate_size": 3420,
|
| 364 |
+
"is_decoder": false,
|
| 365 |
+
"is_encoder_decoder": false,
|
| 366 |
+
"label2id": {
|
| 367 |
+
"LABEL_0": 0,
|
| 368 |
+
"LABEL_1": 1
|
| 369 |
+
},
|
| 370 |
+
"length_penalty": 1.0,
|
| 371 |
+
"max_length": 20,
|
| 372 |
+
"min_length": 0,
|
| 373 |
+
"model_type": "qwen2_5_omni_vision_encoder",
|
| 374 |
+
"no_repeat_ngram_size": 0,
|
| 375 |
+
"num_beam_groups": 1,
|
| 376 |
+
"num_beams": 1,
|
| 377 |
+
"num_heads": 16,
|
| 378 |
+
"num_return_sequences": 1,
|
| 379 |
+
"out_hidden_size": 3584,
|
| 380 |
+
"output_attentions": false,
|
| 381 |
+
"output_hidden_states": false,
|
| 382 |
+
"output_scores": false,
|
| 383 |
+
"pad_token_id": 151643,
|
| 384 |
+
"patch_size": 14,
|
| 385 |
+
"prefix": null,
|
| 386 |
+
"problem_type": null,
|
| 387 |
+
"pruned_heads": {},
|
| 388 |
+
"remove_invalid_values": false,
|
| 389 |
+
"repetition_penalty": 1.0,
|
| 390 |
+
"return_dict": true,
|
| 391 |
+
"return_dict_in_generate": false,
|
| 392 |
+
"sep_token_id": null,
|
| 393 |
+
"spatial_merge_size": 2,
|
| 394 |
+
"spatial_patch_size": 14,
|
| 395 |
+
"suppress_tokens": null,
|
| 396 |
+
"task_specific_params": null,
|
| 397 |
+
"temperature": 1.0,
|
| 398 |
+
"temporal_patch_size": 2,
|
| 399 |
+
"tf_legacy_loss": false,
|
| 400 |
+
"tie_encoder_decoder": false,
|
| 401 |
+
"tie_word_embeddings": true,
|
| 402 |
+
"tokenizer_class": null,
|
| 403 |
+
"tokens_per_second": 25,
|
| 404 |
+
"top_k": 50,
|
| 405 |
+
"top_p": 1.0,
|
| 406 |
+
"torchscript": false,
|
| 407 |
+
"typical_p": 1.0,
|
| 408 |
+
"use_bfloat16": false,
|
| 409 |
+
"window_size": 112
|
| 410 |
+
},
|
| 411 |
+
"vision_end_token_id": 151653,
|
| 412 |
+
"vision_start_token_id": 151652,
|
| 413 |
+
"vision_token_id": 151654
|
| 414 |
+
},
|
| 415 |
+
"token2wav_config": {
|
| 416 |
+
"_attn_implementation_autoset": true,
|
| 417 |
+
"bigvgan_config": {
|
| 418 |
+
"_attn_implementation_autoset": true,
|
| 419 |
+
"_name_or_path": "",
|
| 420 |
+
"add_cross_attention": false,
|
| 421 |
+
"architectures": null,
|
| 422 |
+
"bad_words_ids": null,
|
| 423 |
+
"begin_suppress_tokens": null,
|
| 424 |
+
"bos_token_id": null,
|
| 425 |
+
"chunk_size_feed_forward": 0,
|
| 426 |
+
"cross_attention_hidden_size": null,
|
| 427 |
+
"decoder_start_token_id": null,
|
| 428 |
+
"diversity_penalty": 0.0,
|
| 429 |
+
"do_sample": false,
|
| 430 |
+
"dtype": null,
|
| 431 |
+
"early_stopping": false,
|
| 432 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 433 |
+
"eos_token_id": null,
|
| 434 |
+
"exponential_decay_length_penalty": null,
|
| 435 |
+
"finetuning_task": null,
|
| 436 |
+
"forced_bos_token_id": null,
|
| 437 |
+
"forced_eos_token_id": null,
|
| 438 |
+
"id2label": {
|
| 439 |
+
"0": "LABEL_0",
|
| 440 |
+
"1": "LABEL_1"
|
| 441 |
+
},
|
| 442 |
+
"is_decoder": false,
|
| 443 |
+
"is_encoder_decoder": false,
|
| 444 |
+
"label2id": {
|
| 445 |
+
"LABEL_0": 0,
|
| 446 |
+
"LABEL_1": 1
|
| 447 |
+
},
|
| 448 |
+
"length_penalty": 1.0,
|
| 449 |
+
"max_length": 20,
|
| 450 |
+
"mel_dim": 80,
|
| 451 |
+
"min_length": 0,
|
| 452 |
+
"model_type": "qwen2_5_omni_bigvgan",
|
| 453 |
+
"no_repeat_ngram_size": 0,
|
| 454 |
+
"num_beam_groups": 1,
|
| 455 |
+
"num_beams": 1,
|
| 456 |
+
"num_return_sequences": 1,
|
| 457 |
+
"output_attentions": false,
|
| 458 |
+
"output_hidden_states": false,
|
| 459 |
+
"output_scores": false,
|
| 460 |
+
"pad_token_id": 151643,
|
| 461 |
+
"prefix": null,
|
| 462 |
+
"problem_type": null,
|
| 463 |
+
"pruned_heads": {},
|
| 464 |
+
"remove_invalid_values": false,
|
| 465 |
+
"repetition_penalty": 1.0,
|
| 466 |
+
"resblock_dilation_sizes": [
|
| 467 |
+
[
|
| 468 |
+
1,
|
| 469 |
+
3,
|
| 470 |
+
5
|
| 471 |
+
],
|
| 472 |
+
[
|
| 473 |
+
1,
|
| 474 |
+
3,
|
| 475 |
+
5
|
| 476 |
+
],
|
| 477 |
+
[
|
| 478 |
+
1,
|
| 479 |
+
3,
|
| 480 |
+
5
|
| 481 |
+
]
|
| 482 |
+
],
|
| 483 |
+
"resblock_kernel_sizes": [
|
| 484 |
+
3,
|
| 485 |
+
7,
|
| 486 |
+
11
|
| 487 |
+
],
|
| 488 |
+
"return_dict": true,
|
| 489 |
+
"return_dict_in_generate": false,
|
| 490 |
+
"sep_token_id": null,
|
| 491 |
+
"suppress_tokens": null,
|
| 492 |
+
"task_specific_params": null,
|
| 493 |
+
"temperature": 1.0,
|
| 494 |
+
"tf_legacy_loss": false,
|
| 495 |
+
"tie_encoder_decoder": false,
|
| 496 |
+
"tie_word_embeddings": true,
|
| 497 |
+
"tokenizer_class": null,
|
| 498 |
+
"top_k": 50,
|
| 499 |
+
"top_p": 1.0,
|
| 500 |
+
"torchscript": false,
|
| 501 |
+
"typical_p": 1.0,
|
| 502 |
+
"upsample_initial_channel": 1536,
|
| 503 |
+
"upsample_kernel_sizes": [
|
| 504 |
+
11,
|
| 505 |
+
7,
|
| 506 |
+
4,
|
| 507 |
+
4,
|
| 508 |
+
4,
|
| 509 |
+
4
|
| 510 |
+
],
|
| 511 |
+
"upsample_rates": [
|
| 512 |
+
5,
|
| 513 |
+
3,
|
| 514 |
+
2,
|
| 515 |
+
2,
|
| 516 |
+
2,
|
| 517 |
+
2
|
| 518 |
+
],
|
| 519 |
+
"use_bfloat16": false,
|
| 520 |
+
"use_bias_at_final": false
|
| 521 |
+
},
|
| 522 |
+
"dit_config": {
|
| 523 |
+
"_attn_implementation_autoset": true,
|
| 524 |
+
"_name_or_path": "",
|
| 525 |
+
"add_cross_attention": false,
|
| 526 |
+
"architectures": null,
|
| 527 |
+
"bad_words_ids": null,
|
| 528 |
+
"begin_suppress_tokens": null,
|
| 529 |
+
"block_size": 24,
|
| 530 |
+
"bos_token_id": null,
|
| 531 |
+
"chunk_size_feed_forward": 0,
|
| 532 |
+
"cross_attention_hidden_size": null,
|
| 533 |
+
"decoder_start_token_id": null,
|
| 534 |
+
"depth": 22,
|
| 535 |
+
"dim": 1024,
|
| 536 |
+
"diversity_penalty": 0.0,
|
| 537 |
+
"do_sample": false,
|
| 538 |
+
"dropout": 0.1,
|
| 539 |
+
"dtype": "float32",
|
| 540 |
+
"early_stopping": false,
|
| 541 |
+
"emb_dim": 512,
|
| 542 |
+
"enc_attention_channels": 64,
|
| 543 |
+
"enc_channels": [
|
| 544 |
+
256,
|
| 545 |
+
256,
|
| 546 |
+
256,
|
| 547 |
+
256,
|
| 548 |
+
768
|
| 549 |
+
],
|
| 550 |
+
"enc_dilations": [
|
| 551 |
+
1,
|
| 552 |
+
2,
|
| 553 |
+
3,
|
| 554 |
+
4,
|
| 555 |
+
1
|
| 556 |
+
],
|
| 557 |
+
"enc_dim": 128,
|
| 558 |
+
"enc_emb_dim": 192,
|
| 559 |
+
"enc_global_context": true,
|
| 560 |
+
"enc_kernel_sizes": [
|
| 561 |
+
5,
|
| 562 |
+
3,
|
| 563 |
+
3,
|
| 564 |
+
3,
|
| 565 |
+
1
|
| 566 |
+
],
|
| 567 |
+
"enc_lin_neurons": 192,
|
| 568 |
+
"enc_res2net_scale": 2,
|
| 569 |
+
"enc_se_channels": 64,
|
| 570 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 571 |
+
"eos_token_id": null,
|
| 572 |
+
"exponential_decay_length_penalty": null,
|
| 573 |
+
"ff_mult": 2,
|
| 574 |
+
"finetuning_task": null,
|
| 575 |
+
"forced_bos_token_id": null,
|
| 576 |
+
"forced_eos_token_id": null,
|
| 577 |
+
"head_dim": 64,
|
| 578 |
+
"heads": 16,
|
| 579 |
+
"hidden_size": 1024,
|
| 580 |
+
"id2label": {
|
| 581 |
+
"0": "LABEL_0",
|
| 582 |
+
"1": "LABEL_1"
|
| 583 |
+
},
|
| 584 |
+
"is_decoder": false,
|
| 585 |
+
"is_encoder_decoder": false,
|
| 586 |
+
"label2id": {
|
| 587 |
+
"LABEL_0": 0,
|
| 588 |
+
"LABEL_1": 1
|
| 589 |
+
},
|
| 590 |
+
"length_penalty": 1.0,
|
| 591 |
+
"look_ahead_layers": [
|
| 592 |
+
10
|
| 593 |
+
],
|
| 594 |
+
"look_backward_layers": [
|
| 595 |
+
0,
|
| 596 |
+
20
|
| 597 |
+
],
|
| 598 |
+
"max_length": 20,
|
| 599 |
+
"max_position_embeddings": 32768,
|
| 600 |
+
"mel_dim": 80,
|
| 601 |
+
"min_length": 0,
|
| 602 |
+
"model_type": "qwen2_5_omni_dit",
|
| 603 |
+
"no_repeat_ngram_size": 0,
|
| 604 |
+
"num_attention_heads": 16,
|
| 605 |
+
"num_beam_groups": 1,
|
| 606 |
+
"num_beams": 1,
|
| 607 |
+
"num_embeds": 8193,
|
| 608 |
+
"num_hidden_layers": 22,
|
| 609 |
+
"num_return_sequences": 1,
|
| 610 |
+
"output_attentions": false,
|
| 611 |
+
"output_hidden_states": false,
|
| 612 |
+
"output_scores": false,
|
| 613 |
+
"pad_token_id": 151643,
|
| 614 |
+
"prefix": null,
|
| 615 |
+
"problem_type": null,
|
| 616 |
+
"pruned_heads": {},
|
| 617 |
+
"remove_invalid_values": false,
|
| 618 |
+
"repeats": 2,
|
| 619 |
+
"repetition_penalty": 1.0,
|
| 620 |
+
"return_dict": true,
|
| 621 |
+
"return_dict_in_generate": false,
|
| 622 |
+
"rope_theta": 10000.0,
|
| 623 |
+
"sep_token_id": null,
|
| 624 |
+
"suppress_tokens": null,
|
| 625 |
+
"task_specific_params": null,
|
| 626 |
+
"temperature": 1.0,
|
| 627 |
+
"tf_legacy_loss": false,
|
| 628 |
+
"tie_encoder_decoder": false,
|
| 629 |
+
"tie_word_embeddings": true,
|
| 630 |
+
"tokenizer_class": null,
|
| 631 |
+
"top_k": 50,
|
| 632 |
+
"top_p": 1.0,
|
| 633 |
+
"torchscript": false,
|
| 634 |
+
"typical_p": 1.0,
|
| 635 |
+
"use_bfloat16": false
|
| 636 |
+
},
|
| 637 |
+
"dtype": "bfloat16",
|
| 638 |
+
"model_type": "qwen2_5_omni_token2wav",
|
| 639 |
+
"pad_token_id": 151643
|
| 640 |
+
},
|
| 641 |
+
"transformers_version": "4.57.6"
|
| 642 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151643,
|
| 5 |
+
151645
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "4.57.6"
|
| 8 |
+
}
|
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:d2bb20bc5fc304d852732b5421f63c0d1fe7d196581c56ee1a6b516d4cb67e61
|
| 3 |
+
size 4985055536
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7af9ac7da5af514d8b36cb3bfde3e676eb8e33aaf00c414ddd547b5a12e8c039
|
| 3 |
+
size 4991496832
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:705e3d5d3fbbb81ddcb499f2bd989c8fb095bf5b5efcb3779fe8094fbe3d8cf6
|
| 3 |
+
size 4991496936
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e0f1b48db7d20a5ed8ed81bfd0329217676d90eefa6139e3d27bf70e4a17581
|
| 3 |
+
size 2895740064
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 300,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.26862954,
|
| 15 |
+
0.26130258,
|
| 16 |
+
0.27577711
|
| 17 |
+
],
|
| 18 |
+
"max_pixels": 12845056,
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"min_pixels": 3136,
|
| 21 |
+
"n_fft": 400,
|
| 22 |
+
"n_samples": 4800000,
|
| 23 |
+
"nb_max_frames": 30000,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"padding_value": 0.0,
|
| 26 |
+
"patch_size": 14,
|
| 27 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
| 28 |
+
"return_attention_mask": true,
|
| 29 |
+
"sampling_rate": 16000,
|
| 30 |
+
"temporal_patch_size": 2
|
| 31 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 18 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 19 |
+
"audio_token": "<|AUDIO|>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<|IMAGE|>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"video_token": "<|VIDEO|>",
|
| 36 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 37 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 38 |
+
}
|
spk_dict.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
|
| 3 |
+
size 259544
|
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 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 197 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 198 |
+
"audio_token": "<|AUDIO|>",
|
| 199 |
+
"bos_token": null,
|
| 200 |
+
"clean_up_tokenization_spaces": false,
|
| 201 |
+
"eos_token": "<|im_end|>",
|
| 202 |
+
"errors": "replace",
|
| 203 |
+
"extra_special_tokens": {
|
| 204 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 205 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 206 |
+
"audio_token": "<|AUDIO|>",
|
| 207 |
+
"image_token": "<|IMAGE|>",
|
| 208 |
+
"video_token": "<|VIDEO|>",
|
| 209 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 210 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 211 |
+
},
|
| 212 |
+
"image_token": "<|IMAGE|>",
|
| 213 |
+
"model_max_length": 32768,
|
| 214 |
+
"pad_token": "<|endoftext|>",
|
| 215 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
| 216 |
+
"split_special_tokens": false,
|
| 217 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 218 |
+
"unk_token": null,
|
| 219 |
+
"video_token": "<|VIDEO|>",
|
| 220 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 221 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 222 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 300,
|
| 3 |
+
"crop_size": null,
|
| 4 |
+
"data_format": "channels_first",
|
| 5 |
+
"default_to_square": true,
|
| 6 |
+
"device": null,
|
| 7 |
+
"dither": 0.0,
|
| 8 |
+
"do_center_crop": null,
|
| 9 |
+
"do_convert_rgb": true,
|
| 10 |
+
"do_normalize": true,
|
| 11 |
+
"do_pad": null,
|
| 12 |
+
"do_rescale": true,
|
| 13 |
+
"do_resize": true,
|
| 14 |
+
"do_sample_frames": false,
|
| 15 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 16 |
+
"feature_size": 128,
|
| 17 |
+
"fps": null,
|
| 18 |
+
"hop_length": 160,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.48145466,
|
| 21 |
+
0.4578275,
|
| 22 |
+
0.40821073
|
| 23 |
+
],
|
| 24 |
+
"image_std": [
|
| 25 |
+
0.26862954,
|
| 26 |
+
0.26130258,
|
| 27 |
+
0.27577711
|
| 28 |
+
],
|
| 29 |
+
"input_data_format": null,
|
| 30 |
+
"max_frames": 768,
|
| 31 |
+
"max_pixels": 12845056,
|
| 32 |
+
"merge_size": 2,
|
| 33 |
+
"min_frames": 4,
|
| 34 |
+
"min_pixels": 3136,
|
| 35 |
+
"n_fft": 400,
|
| 36 |
+
"n_samples": 4800000,
|
| 37 |
+
"nb_max_frames": 30000,
|
| 38 |
+
"num_frames": null,
|
| 39 |
+
"pad_size": null,
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"padding_value": 0.0,
|
| 42 |
+
"patch_size": 14,
|
| 43 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
| 44 |
+
"resample": 3,
|
| 45 |
+
"rescale_factor": 0.00392156862745098,
|
| 46 |
+
"return_attention_mask": true,
|
| 47 |
+
"return_metadata": false,
|
| 48 |
+
"sampling_rate": 16000,
|
| 49 |
+
"size": {
|
| 50 |
+
"longest_edge": 12845056,
|
| 51 |
+
"shortest_edge": 3136
|
| 52 |
+
},
|
| 53 |
+
"size_divisor": null,
|
| 54 |
+
"temporal_patch_size": 2,
|
| 55 |
+
"video_metadata": null,
|
| 56 |
+
"video_processor_type": "Qwen2VLVideoProcessor"
|
| 57 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|