README.md

metadata

license: apache-2.0
language:
  - en
tags:
  - trl
  - sft
  - abliterated
  - uncensored
  - mlx
  - mlx-my-repo
base_model: huihui-ai/Huihui-Jan-v1-4B-abliterated
pipeline_tag: text-generation
library_name: transformers

Eldadalbajob/Huihui-Jan-v1-4B-abliterated-mlx-fp16

The Model Eldadalbajob/Huihui-Jan-v1-4B-abliterated-mlx-fp16 was converted to MLX format from huihui-ai/Huihui-Jan-v1-4B-abliterated using mlx-lm version 0.26.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Eldadalbajob/Huihui-Jan-v1-4B-abliterated-mlx-fp16")

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)