Downloads · 30 days
0
Smol-reason-LoRA
Sweaterdog/Smol-reason-LoRA
Smol-reason-LoRA is a machine learning model from Sweaterdog. 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.
When making the Andy series of models, I have been using PPO techniques to train models.
Access
Public
Updated Apr 4, 2025
Repo size
490 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors479 MB · 97%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 13, 2025
- Updated
- Apr 4, 2025
- SHA
- feea8388
Model card
From the Hugging Face model README
🧠 Smol-reason, a 3B model test for future models 🧠
Why?
When making the Andy series of models, I have been using PPO techniques to train models.
But as the bleeding edge of small models is becoming clear, reasoning models are the winners.
So, in order to learn the nuances of training models, I decided to train a small 3B model using GRPO techniques instead of PPO.
What do I do with the LoRA?
This LoRA was made so others can train off of this GPRO model, and can be used for any purpose.
- License
- apache-2.0
- Created
- Mar 13, 2025
- Updated
- Apr 4, 2025