README.md

metadata

language:
  - en
  - ko
license: llama3.1
tags:
  - llama-3.1
  - ncsoft
  - varco
  - mlx
base_model: NCSOFT/Llama-VARCO-8B-Instruct
library_name: transformers

sosoai/Llama-VARCO-8B-Instruct-mlx

The Model sosoai/Llama-VARCO-8B-Instruct-mlx was converted to MLX format from NCSOFT/Llama-VARCO-8B-Instruct using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("sosoai/Llama-VARCO-8B-Instruct-mlx")

prompt = "hello"

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

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