Instructions to use mlx-community/lille-130m-instruct-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/lille-130m-instruct-6bit 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("mlx-community/lille-130m-instruct-6bit") 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 Settings
- LM Studio
- MLX LM
How to use mlx-community/lille-130m-instruct-6bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "mlx-community/lille-130m-instruct-6bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mlx-community/lille-130m-instruct-6bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/lille-130m-instruct-6bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
Download config.json from mlx-community/lille-130m-instruct-6bit: direct link, hf CLI and curl.
- Browser
- Download file 565 Bytes
-
https://huggingface.co/mlx-community/lille-130m-instruct-6bit/resolve/main/config.json
- Command line
-
hf download hf://mlx-community/lille-130m-instruct-6bit/config.json
-
curl -L -o config.json https://huggingface.co/mlx-community/lille-130m-instruct-6bit/resolve/main/config.json
565 Bytes
| { | |
| "architectures": [ | |
| "LilleForCausalLM" | |
| ], | |
| "block_size": 512, | |
| "dropout": 0.0, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "lille-130m", | |
| "n_embd": 640, | |
| "n_head": 10, | |
| "n_kv_heads": 2, | |
| "n_layer": 24, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine" | |
| }, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.3", | |
| "vocab_size": 32768 | |
| } |