README.md

metadata

language:
  - en
  - ko
library_name: transformers
license: cc-by-nc-4.0
pipeline_tag: text-generation
developers: Kanana LLM
training_regime: bf16 mixed precision
base_model: huihui-ai/kanana-nano-2.1b-instruct-abliterated
tags:
  - abliterated
  - uncensored
  - mlx
  - mlx-my-repo

KYUNGYONG/kanana-nano-2.1b-instruct-abliterated-4bit

The Model KYUNGYONG/kanana-nano-2.1b-instruct-abliterated-4bit was converted to MLX format from huihui-ai/kanana-nano-2.1b-instruct-abliterated using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/kanana-nano-2.1b-instruct-abliterated-4bit")

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)