Janhq Jan v3.5 4B MLX 4bit

--- license: apache-2.0 language: - en base_model: janhq/Jan-v3.5-4B pipeline_tag: text-generation library_name: mlx tags: - math - identity - mlx --- # schnow265/janhq_Jan-v3.5-4B-MLX-4bit This model [schnow265/janhq_Jan-v3.5-4B-MLX-4bit](https://huggingface.co/schnow265/janhq_Jan-v3.5-4B-MLX-4bit) was converted to MLX format from [janhq/Jan-v3.5-4B](https://huggingface.co/janhq/Jan-v3.5-4B) using mlx-lm version **0.31.3**. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("schnow265/janhq_Jan-v3.5-4B-MLX-4bit") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_dict=False, ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```