thr3a's picture
fb1846a00138b6f55669e85a289a2777577eaecbca60cc0e2e33bee2ccf69e74
6af17c1 verified
|
raw
history blame
993 Bytes
metadata
license: gemma
library_name: transformers
tags:
  - conversational
  - mlx
base_model: AXCXEPT/EZO-Humanities-9B-gemma-2-it
pipeline_tag: text-generation

thr3a/EZO-Humanities-9B-gemma-2-it-4b-mlx

The Model thr3a/EZO-Humanities-9B-gemma-2-it-4b-mlx was converted to MLX format from AXCXEPT/EZO-Humanities-9B-gemma-2-it using mlx-lm version 0.18.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("thr3a/EZO-Humanities-9B-gemma-2-it-4b-mlx")

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)