metadata
library_name: transformers
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- mlx
- mlx-my-repo
base_model: DreadPoor/Famino-12B-Model_Stock
hobaratio/Famino-12B-Model_Stock-mlx-4Bit
The Model hobaratio/Famino-12B-Model_Stock-mlx-4Bit was converted to MLX format from DreadPoor/Famino-12B-Model_Stock using mlx-lm version 0.28.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("hobaratio/Famino-12B-Model_Stock-mlx-4Bit")
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)