Audio-Text-to-Text
Transformers
Safetensors
Chinese
English
qwen2_5_omni_thinker
speech
audio
speech-evaluation
expressive-speech
mandarin
chain-of-thought
ceaeval
Instructions to use TianRW/CEAEval-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TianRW/CEAEval-Model with Transformers:
# Load model directly from transformers import AutoTokenizer, GatedAttenQwen2_5omnithinker tokenizer = AutoTokenizer.from_pretrained("TianRW/CEAEval-Model") model = GatedAttenQwen2_5omnithinker.from_pretrained("TianRW/CEAEval-Model") - Notebooks
- Google Colab
- Kaggle
File size: 3,380 Bytes
7b20070 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | {
"_attn_implementation_autoset": true,
"architectures": [
"GatedAttenQwen2_5omnithinker"
],
"audio_config": {
"_attn_implementation_autoset": true,
"activation_dropout": 0.0,
"activation_function": "gelu",
"attention_dropout": 0.0,
"d_model": 1280,
"dropout": 0.0,
"dtype": "float32",
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"init_std": 0.02,
"initializer_range": 0.02,
"max_source_positions": 1500,
"model_type": "qwen2_5_omni_audio_encoder",
"n_window": 100,
"num_hidden_layers": 32,
"num_mel_bins": 128,
"output_dim": 3584,
"scale_embedding": false
},
"audio_end_token_id": 151648,
"audio_start_token_id": 151647,
"audio_token_index": 151646,
"bos_token_id": 151644,
"dtype": "float32",
"eos_token_id": 151645,
"ignore_index": -100,
"image_token_index": 151655,
"init_std": 0.02,
"initializer_range": 0.02,
"model_type": "qwen2_5_omni_thinker",
"pad_token_id": 151643,
"position_id_per_seconds": 25,
"seconds_per_chunk": 2,
"text_config": {
"attention_dropout": 0.0,
"dtype": "float32",
"hidden_act": "silu",
"hidden_size": 3584,
"init_std": 0.02,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2_5_omni_text",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
},
"transformers_version": "4.57.0.dev0",
"user_token_id": 872,
"video_token_index": 151656,
"vision_config": {
"_attn_implementation_autoset": true,
"depth": 32,
"dtype": "float32",
"embed_dim": 1280,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"init_std": 0.02,
"initializer_range": 0.02,
"intermediate_size": 3420,
"model_type": "qwen2_5_omni_vision_encoder",
"num_heads": 16,
"out_hidden_size": 3584,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 25,
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654
}
|