metadata
license: apache-2.0
language:
- en
- es
tags:
- moe
- code
- math
- vllm
- mxfp4
- pruning
- scalai
- mlx
- mlx-my-repo
datasets:
- HuggingFaceH4/CodeAlpaca_20K
base_model: Scalai/scal-lite-60b-code
Wwayu/scal-lite-60b-code-mlx-8Bit
The Model Wwayu/scal-lite-60b-code-mlx-8Bit was converted to MLX format from Scalai/scal-lite-60b-code using mlx-lm version 0.29.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Wwayu/scal-lite-60b-code-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)