Downloads · 30 days
23
8% of all-time downloads
gemma-2-9b-it-WPO-HB-8bit
sigjhl/gemma-2-9b-it-WPO-HB-8bit
gemma-2-9b-it-WPO-HB-8bit is a text generation model from sigjhl. Use it when you need the model to write or continue text. It is set up for transformers.
The Model sigjhl/gemma-2-9b-it-WPO-HB-8bit was converted to MLX format from wzhouad/gemma-2-9b-it-WPO-HB using mlx-lm version 0.18.1.
All-time downloads
295
Public
Parameters
9.2B
9.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.8 GB · 100%
Parameter types
How the weights are stored.
U329.2B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
sigjhl/gemma-2-9b-it-WPO-HB-8bit
The Model sigjhl/gemma-2-9b-it-WPO-HB-8bit was converted to MLX format from wzhouad/gemma-2-9b-it-WPO-HB using mlx-lm version 0.18.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sigjhl/gemma-2-9b-it-WPO-HB-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Task
- Text Generation
- Library
- transformers
- Type
- gemma2
- Created
- Sep 5, 2024
- Updated
- Sep 5, 2024