DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16/README.md

language, license, pipeline_tag, tags, base_model, extra_gated_fields

language	license	pipeline_tag	tags	base_model	extra_gated_fields
en	llama3.1	text-generation	roleplay llama3 sillytavern idol facebook meta pytorch llama llama-3 mlx mlx-my-repo	aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored	First Name Last Name Date of birth Country Affiliation Job title text text date_picker country text type options select Student Research Graduate AI researcher AI developer/engineer Reporter Other

isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16

The Model isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-mlx-fp16 was converted to MLX format from aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored using mlx-lm version 0.29.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("isetnefret/DarkIdol-Llama-3.1-8B-Instruct-1.3-Uncensored-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)