metadata
library_name: transformers
base_model: Sao10K/70B-L3.3-Cirrus-x1
tags:
- generated_from_trainer
- mlx
- mlx-my-repo
license: llama3.3
model-index:
- name: 70B-L3.3-Cirrus-x1
results: []
Wwayu/70B-L3.3-Cirrus-x1-mlx-4Bit
The Model Wwayu/70B-L3.3-Cirrus-x1-mlx-4Bit was converted to MLX format from Sao10K/70B-L3.3-Cirrus-x1 using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Wwayu/70B-L3.3-Cirrus-x1-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)