mlx-community/RakutenAI-7B-MLX-4bit

This model was converted to MLX format from Rakuten/RakutenAI-7B using mlx-lm version 0.31.0. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/RakutenAI-7B-MLX-4bit")

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)

Inference: M3 Ultra
==========
, I'm a newbie to the forum and I'm looking for some help. I'm trying to create a 3d model of a human body. I've been using the 3d human model from the 3d content library and I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to create a model of a human body. I've been able to
==========
Prompt: 3 tokens, 49.961 tokens-per-sec
Generation: 256 tokens, 128.771 tokens-per-sec
Peak memory: 4.255 GB