README.md

metadata

base_model: Tesslate/Tessa-T1-32B
tags:
  - text-generation-inference
  - transformers
  - qwen2
  - trl
  - mlx
license: apache-2.0
language:
  - en
datasets:
  - Tesslate/Tessa-T1-Dataset
pipeline_tag: text-generation
library_name: mlx

mlx-community/Tessa-T1-32B-mlx-8bit

This model mlx-community/Tessa-T1-32B-mlx-8bit was converted to MLX format from Tesslate/Tessa-T1-32B using mlx-lm version 0.22.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Tessa-T1-32B-mlx-8bit")

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)