Downloads · 30 days
25
10% of all-time downloads
Breeze-7B-32k-Base-v1_0-8bit
derektu123/Breeze-7B-32k-Base-v1_0-8bit
Breeze-7B-32k-Base-v1_0-8bit is a text generation model from derektu123. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
The Model derektu123/Breeze-7B-32k-Base-v10-8bit was converted to MLX format from MediaTek-Research/Breeze-7B-32k-Base-v10 using mlx-lm version 0.14.3.
All-time downloads
242
Public
Parameters
7.5B
8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8 GB · 100%
Parameter types
How the weights are stored.
U327.5B · 100%
Model card
From the Hugging Face model README
derektu123/Breeze-7B-32k-Base-v1_0-8bit
The Model derektu123/Breeze-7B-32k-Base-v1_0-8bit was converted to MLX format from MediaTek-Research/Breeze-7B-32k-Base-v1_0 using mlx-lm version 0.14.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("derektu123/Breeze-7B-32k-Base-v1_0-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Task
- Text Generation
- Library
- mlx
- Type
- mistral
- License
- apache-2.0
- Languages
- zh, en
- Created
- Jun 16, 2024
- Updated
- Jun 16, 2024