introvoyz041's picture
Upload README.md with huggingface_hub
4ce4989 verified
metadata
library_name: transformers
license: apache-2.0
language:
  - en
  - fr
  - es
  - it
  - pt
  - zh
  - ar
  - ru
tags:
  - mlx
  - mlx
  - mlx-my-repo
base_model: lmstudio-community/SmolLM3-3B-MLX-8bit

introvoyz041/SmolLM3-3B-MLX-8bit-mlx-8Bit

The Model introvoyz041/SmolLM3-3B-MLX-8bit-mlx-8Bit was converted to MLX format from lmstudio-community/SmolLM3-3B-MLX-8bit using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/SmolLM3-3B-MLX-8bit-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)