Text Generation
MLX
Safetensors
English
Chinese
llama
code
math
conversational
Eval Results (legacy)
4-bit precision
Instructions to use IvanHU/YuLan-Mini-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use IvanHU/YuLan-Mini-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("IvanHU/YuLan-Mini-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 IvanHU/YuLan-Mini-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 "IvanHU/YuLan-Mini-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "IvanHU/YuLan-Mini-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "IvanHU/YuLan-Mini-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "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 | |
| }, | |
| "102": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "103": { | |
| "content": "<reasoning_step>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "104": { | |
| "content": "<|start_header_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "105": { | |
| "content": "<|end_header_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "106": { | |
| "content": "<|eot_id|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "bos_token": "<s>", | |
| "chat_template": "{% if messages[0]['role'] == 'system' %}\n {% set offset = 1 %}\n{% else %}\n {% set offset = 0 %}\n{% endif %}\n\n{{ bos_token }}\n{% for message in messages %}\n {% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}\n {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n {% endif %}\n\n {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}\n{% endfor %}\n\n{% if add_generation_prompt %}\n {{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}\n{% endif %}", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "extra_special_tokens": {}, | |
| "legacy": true, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "padding_side": "right", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "LlamaTokenizerFast", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |