Buckets:
| { | |
| "adapter_hidden_size": 8192, | |
| "architectures": [ | |
| "MossAudioModel" | |
| ], | |
| "audio_config": { | |
| "_attn_implementation": "eager", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "attention_dropout": 0.1, | |
| "d_model": 1280, | |
| "deepstack_encoder_layer_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "downsample_hidden_size": 480, | |
| "downsample_rate": 8, | |
| "dropout": 0.1, | |
| "encoder_attention_heads": 20, | |
| "encoder_attention_window_size": 100, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layers": 32, | |
| "layer_norm_eps": 1e-05, | |
| "max_source_positions": 1500, | |
| "num_mel_bins": 128, | |
| "output_dim": 1280, | |
| "pretrained_path": "" | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_moss_audio.MossAudioConfig", | |
| "AutoProcessor": "processing_moss_audio.MossAudioProcessor" | |
| }, | |
| "bos_token_id": 151643, | |
| "deepstack_num_inject_layers": 3, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "ignore_index": -100, | |
| "language_config": { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "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", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 36, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "model_type": "moss_audio", | |
| "num_hidden_layers": 36, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "vocab_size": 151936 | |
| } | |
Xet Storage Details
- Size:
- 2.72 kB
- Xet hash:
- 5076f649ff4acb9f4b78b2f70516f08344b8a11e9fde0fd8df671e0b83ca4a7e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.