README.md

metadata

base_model: sophosympatheia/Nova-Tempus-70B-v0.2
library_name: transformers
tags:
  - mergekit
  - merge
  - not-for-all-audiences
  - mlx
license: llama3.3
language:
  - en

beezu/Nova-Tempus-70B-v0.2-MLX-3Bit

The Model beezu/Nova-Tempus-70B-v0.2-MLX-3Bit was converted to MLX format from sophosympatheia/Nova-Tempus-70B-v0.2 using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("beezu/Nova-Tempus-70B-v0.2-MLX-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)