Downloads · 30 days
20
1% of all-time downloads
Llemma-reward-model
tkitsers/Llemma-reward-model
Llemma-reward-model is a machine learning model from tkitsers. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a reward model finetuned on Llemma-34b. To score the steps, pass encoded text = question + solution as input.
All-time downloads
2K
Public
Parameters
33.7B
67.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors67.5 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Sep 8, 2024
- Updated
- Sep 9, 2024
- SHA
- abea6165
Model card
From the Hugging Face model README
This is a reward model finetuned on Llemma-34b. To score the steps, pass encoded text = question + solution as input.
rewards = model(text).mean(dim=-1).sigmoid()[index]
Where index is the positions for special end tokens of each step.
- Type
- llama
- License
- apache-2.0
- Created
- Sep 8, 2024
- Updated
- Sep 9, 2024