metadata
license: llama3.3
base_model: Steelskull/L3.3-Shakudo-70b
tags:
- mlx
mrtoots/Steelskull-L3.3-Shakudo-70b-mlx-8Bit
The Model mrtoots/Steelskull-L3.3-Shakudo-70b-mlx-8Bit was converted to MLX format from Steelskull/L3.3-Shakudo-70b using mlx-lm version 0.26.4.
Toots' Note:
Please follow and support Steelskull's work if you like it!
Settings and how best to run found on the original model page.
🦛 If you want a free consulting session, fill out this form to get in touch! 🤗
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mrtoots/L3.3-Shakudo-70b-mlx-8Bit")
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)