7.7 GB
10 files
Updated 2 months ago
README.md

mlx-community/SakanaAI-EvoLLM-JP-v1-7B-8bit

The Model mlx-community/SakanaAI-EvoLLM-JP-v1-7B-8bit was converted to MLX format from SakanaAI/EvoLLM-JP-v1-7B using mlx-lm version 0.19.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SakanaAI-EvoLLM-JP-v1-7B-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)
Total size
7.7 GB
Files
10
Last updated
Jul 8
Pre-warmed CDN
US EU US EU

Contributors