Tessa-T1-14B-mlx-bf16/README.md

base_model, tags, license, language, datasets, library_name, pipeline_tag

base_model	tags	license	language	datasets	library_name	pipeline_tag
Tesslate/Tessa-T1-14B	text-generation-inference transformers qwen2 trl mlx	apache-2.0	en	Tesslate/Tessa-T1-Dataset	mlx	text-generation

mlx-community/Tessa-T1-14B-mlx-bf16

This model mlx-community/Tessa-T1-14B-mlx-bf16 was converted to MLX format from Tesslate/Tessa-T1-14B 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-T1-14B-mlx-bf16")

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)