README.md

metadata

license: apache-2.0
language:
  - en
base_model: ReadyArt/Gaslit-Transgression-24B-v1.0
base_model_relation: finetune
pipeline_tag: text-generation
tags:
  - nsfw
  - explicit
  - roleplay
  - unaligned
  - dangerous
  - ERP
  - mlx
library_name: mlx

Beridar/ReadyArt-Gaslit-Transgression-24B-v1.0-mlx-6bit

This model Beridar/ReadyArt-Gaslit-Transgression-24B-v1.0-mlx-6bit was converted to MLX format from ReadyArt/Gaslit-Transgression-24B-v1.0 using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Beridar/ReadyArt-Gaslit-Transgression-24B-v1.0-mlx-6bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)