serpro's picture
Upload README.md with huggingface_hub
22f2e4b verified
|
Raw History Blame Contribute Delete
1 kB
metadata
library_name: transformers
license: llama3
base_model: Sao10K/L3.3-70B-Euryale-v2.3
tags:
  - generated_from_trainer
  - mlx
  - mlx-my-repo
model-index:
  - name: L3.3-70B-Euryale-v2.3
    results: []

serpro/L3.3-70B-Euryale-v2.3-mlx-8Bit

The Model serpro/L3.3-70B-Euryale-v2.3-mlx-8Bit was converted to MLX format from Sao10K/L3.3-70B-Euryale-v2.3 using mlx-lm version 0.22.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("serpro/L3.3-70B-Euryale-v2.3-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)