Instructions to use vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-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("vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-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 Settings
- LM Studio
- MLX LM
How to use vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-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 "vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vqstudio/Bielik-1.5B-v3.0-Instruct-MLX-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Atomic Chat
| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "add_prefix_space": null, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<|im_start|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "</tool_call>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<tool_call>", | |
| "</tool_call>" | |
| ], | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "extra_special_tokens": {}, | |
| "legacy": true, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "</s>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "LlamaTokenizerFast", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |