Instructions to use FluffyAIcode/Kakeya-OProver-Stage4-Repair-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use FluffyAIcode/Kakeya-OProver-Stage4-Repair-SFT with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("m-a-p/OProver-8B") model = PeftModel.from_pretrained(base_model, "FluffyAIcode/Kakeya-OProver-Stage4-Repair-SFT") - Notebooks
- Google Colab
- Kaggle
Link content-addressed release manifest
Browse files
README.md
CHANGED
|
@@ -111,3 +111,7 @@ Small, single-seed strict suites cannot establish broad theorem-proving capabili
|
|
| 111 |
## Attribution
|
| 112 |
|
| 113 |
Base model: m-a-p/OProver-8B (Apache-2.0). Training data derives from Mathlib at `360da6fa66c1273b76b6b2d8c5666fd5ac2e3b56` (Apache-2.0). See `NOTICE`.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
## Attribution
|
| 112 |
|
| 113 |
Base model: m-a-p/OProver-8B (Apache-2.0). Training data derives from Mathlib at `360da6fa66c1273b76b6b2d8c5666fd5ac2e3b56` (Apache-2.0). See `NOTICE`.
|
| 114 |
+
|
| 115 |
+
## Release Manifest
|
| 116 |
+
|
| 117 |
+
The content-addressed public/private boundary and immutable asset references are in [`release-manifest.json`](./blob/main/release-manifest.json).
|