README.md

metadata

library_name: mlx
tags:
  - mergekit
  - merge
  - llama 3.1
  - llama-3
  - llama3
  - llama-3.1
  - mlx
base_model: DavidAU/LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B
pipeline_tag: text-generation

LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B-q8-mlx

This model LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B-q8-mlx was converted to MLX format from DavidAU/LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("LLama-3.1-128k-Darkest-Planet-Uncensored-16.5B-q8-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)