Instructions to use 4bit/Qwen-Audio-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 4bit/Qwen-Audio-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="4bit/Qwen-Audio-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("4bit/Qwen-Audio-Chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use 4bit/Qwen-Audio-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "4bit/Qwen-Audio-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "4bit/Qwen-Audio-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/4bit/Qwen-Audio-Chat
- SGLang
How to use 4bit/Qwen-Audio-Chat with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "4bit/Qwen-Audio-Chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "4bit/Qwen-Audio-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "4bit/Qwen-Audio-Chat" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "4bit/Qwen-Audio-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 4bit/Qwen-Audio-Chat with Docker Model Runner:
docker model run hf.co/4bit/Qwen-Audio-Chat
| { | |
| "_name_or_path": "10302244_iter8000_final/", | |
| "architectures": [ | |
| "QWenLMHeadModel" | |
| ], | |
| "attn_dropout_prob": 0.0, | |
| "audio": { | |
| "add_audio_bos_eos_token": true, | |
| "audio_start_id": 155164, | |
| "avg_pool": true, | |
| "n_ctx": 1500, | |
| "n_head": 20, | |
| "n_layer": 32, | |
| "n_mels": 80, | |
| "n_state": 1280, | |
| "output_dim": 4096 | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_qwen.QWenConfig", | |
| "AutoModelForCausalLM": "modeling_qwen.QWenLMHeadModel" | |
| }, | |
| "bf16": false, | |
| "emb_dropout_prob": 0.0, | |
| "fp16": true, | |
| "fp32": false, | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 22016, | |
| "kv_channels": 128, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 8192, | |
| "model_type": "qwen", | |
| "no_bias": true, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "onnx_safe": null, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 1.0, | |
| "scale_attn_weights": true, | |
| "seq_length": 2048, | |
| "softmax_in_fp32": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_type": "QWenTokenizer", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.32.0", | |
| "use_cache": true, | |
| "use_cache_kernel": false, | |
| "use_cache_quantization": false, | |
| "use_dynamic_ntk": true, | |
| "use_flash_attn": true, | |
| "use_logn_attn": true, | |
| "vocab_size": 155947 | |
| } | |