README.md

metadata

license: cc-by-nc-nd-4.0
tags:
  - generated_from_trainer
  - mlx
datasets:
  - jondurbin/bagel-v0.3
library_name: transformers
base_model: fblgit/UNA-TheBeagle-7b-v1
model-index:
  - name: UNA-TheBeagle-7b-v1
    results: []

morgul/UNA-TheBeagle-7b-v1-Q8-mlx

The Model morgul/UNA-TheBeagle-7b-v1-Q8-mlx was converted to MLX format from fblgit/UNA-TheBeagle-7b-v1 using mlx-lm version 0.19.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("morgul/UNA-TheBeagle-7b-v1-Q8-mlx")

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)