README.md

metadata

base_model: btaskel/Tifa-DeepsexV2-7b-MGRPO-safetensors
language:
  - zh
  - en
library_name: transformers
tags:
  - incremental-pretraining
  - sft
  - reinforcement-learning
  - roleplay
  - cot
  - mlx
  - mlx-my-repo
license: apache-2.0

KYUNGYONG/Tifa-DeepsexV2-7b-MGRPO-safetensors-4bit

The Model KYUNGYONG/Tifa-DeepsexV2-7b-MGRPO-safetensors-4bit was converted to MLX format from btaskel/Tifa-DeepsexV2-7b-MGRPO-safetensors using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("KYUNGYONG/Tifa-DeepsexV2-7b-MGRPO-safetensors-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)