KAT-Dev-3bit / README.md
NexVeridian's picture
Add files using upload-large-folder tool
fc8125f verified
metadata
language:
  - multilingual
license: other
license_name: kwaipilot-license
license_link: LICENSE
library_name: mlx
tags:
  - mlx
pipeline_tag: text-generation
base_model: Kwaipilot/KAT-Dev

NexVeridian/KAT-Dev-3bit

This model NexVeridian/KAT-Dev-3bit was converted to MLX format from Kwaipilot/KAT-Dev using mlx-lm version 0.28.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/KAT-Dev-3bit")

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)