metadata
library_name: transformers
tags:
- mergekit
- merge
- mlx
- mlx-my-repo
base_model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
gonzo404/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-mlx-6Bit
The Model gonzo404/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-mlx-6Bit was converted to MLX format from DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS using mlx-lm version 0.22.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("gonzo404/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-mlx-6Bit")
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)