Downloads · 30 days
49
12% of all-time downloads
Llama-3-8b-Cosmopedia-japanese-4bit
mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit
Llama-3-8b-Cosmopedia-japanese-4bit is a machine learning model from mlx-community. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as llama3.
The Model mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit was converted to MLX format from aixsatoshi/Llama-3-8b-Cosmopedia-japanese using mlx-lm version 0.14.2.
All-time downloads
412
Public
Parameters
8B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U328B · 100%
Model card
From the Hugging Face model README
mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit
The Model mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit was converted to MLX format from aixsatoshi/Llama-3-8b-Cosmopedia-japanese using mlx-lm version 0.14.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Library
- mlx
- Type
- llama
- License
- llama3
- Created
- Jun 12, 2024
- Updated
- Jun 12, 2024