Any-to-Any
Transformers
Safetensors
English
step_audio_2
text-generation
costa
speech-to-speech
spoken-dialogue
speech-token-compression
custom_code
Instructions to use D-YZ/CoSTA-EN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use D-YZ/CoSTA-EN with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("D-YZ/CoSTA-EN", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from D-YZ/CoSTA-EN: direct link, hf CLI and curl.
- Browser
- Download file 1.02 kB
-
https://huggingface.co/D-YZ/CoSTA-EN/resolve/main/config.json
- Command line
-
hf download hf://D-YZ/CoSTA-EN/config.json
-
curl -L -o config.json https://huggingface.co/D-YZ/CoSTA-EN/resolve/main/config.json
1.02 kB
| { | |
| "architectures": [ | |
| "StepAudio2ForCausalLM" | |
| ], | |
| "audio_encoder_config": { | |
| "llm_dim": 3584, | |
| "model_type": "step_audio_2_encoder", | |
| "n_audio_head": 20, | |
| "n_audio_layer": 32, | |
| "n_audio_state": 1280, | |
| "n_codebook_size": 4096 | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_step_audio_2.StepAudio2Config", | |
| "AutoModelForCausalLM": "modeling_step_audio_2.StepAudio2ForCausalLM" | |
| }, | |
| "max_window_layers": null, | |
| "model_type": "step_audio_2", | |
| "sliding_window": 2048, | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "hidden_size": 3584, | |
| "intermediate_size": 18944, | |
| "max_position_embeddings": 16384, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rope_theta": 1000000.0, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 238352 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.49.0", | |
| "use_sliding_window": false | |
| } | |