Update README.md

b551505 verified 2 months ago

979 Bytes

language: en
library_name: mlx
base_model: SicariusSicariiStuff/Assistant_Pepe_70B
tags:
  - mlx
pipeline_tag: text-generation
widget:
  - text: Assistant_Pepe_70B
    output:
      url: >-
        https://huggingface.co/SicariusSicariiStuff/Assistant_Pepe_70B/resolve/main/Images/Assistant_Pepe_70B.png

ailexleon/Assistant_Pepe_70B-mlx-4Bit

Converted to MLX format from SicariusSicariiStuff/Assistant_Pepe_70B using mlx-lm version 0.31.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ailexleon/Assistant_Pepe_70B-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)