README.md

metadata

language:
  - de
  - en
license: llama3
tags:
  - merge
  - mergekit
  - mlx
base_model:
  - cstr/llama3-8b-spaetzle-v31
  - cstr/llama3-8b-spaetzle-v28
  - cstr/llama3-8b-spaetzle-v26
  - cstr/llama3-8b-spaetzle-v20

cstr/llama3-8b-spaetzle-v33-mlx-4bit

The Model cstr/llama3-8b-spaetzle-v33-mlx-4bit was converted to MLX format from cstr/llama3-8b-spaetzle-v33 using mlx-lm version 0.14.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("cstr/llama3-8b-spaetzle-v33-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)