Text Generation
MLX
Safetensors
hunyuan_v1_dense
mlx-my-repo
hunyuan
translation
conversational
4-bit precision
Instructions to use illitan/Hy-MT2-1.8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use illitan/Hy-MT2-1.8B-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("illitan/Hy-MT2-1.8B-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use illitan/Hy-MT2-1.8B-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "illitan/Hy-MT2-1.8B-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "illitan/Hy-MT2-1.8B-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "illitan/Hy-MT2-1.8B-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "bos_token_id": 120000, | |
| "do_sample": true, | |
| "eos_token_id": 120020, | |
| "pad_token_id": 120002, | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.8, | |
| "transformers_version": "4.57.6" | |
| } | |