README.md

metadata

license: apache-2.0
language:
  - en
  - fr
  - de
  - it
  - pt
  - zh
base_model: Hamzah-Asadullah/GenericRPV2-7B
pipeline_tag: text2text-generation
library_name: transformers
tags:
  - merge
  - mergekit
  - rp
  - roleplay
  - roleplaying
  - knowledge-dense
  - code
  - mlx
  - mlx-my-repo

Cozmicalz/GenericRPV2-7B-mlx-4Bit

The Model Cozmicalz/GenericRPV2-7B-mlx-4Bit was converted to MLX format from Hamzah-Asadullah/GenericRPV2-7B using mlx-lm version 0.22.3.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Cozmicalz/GenericRPV2-7B-mlx-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)