Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Open-Orca/OpenOrca
|
| 5 |
+
- teknium/openhermes
|
| 6 |
+
- cognitivecomputations/dolphin
|
| 7 |
+
- jondurbin/airoboros-3.1
|
| 8 |
+
- unalignment/toxic-dpo-v0.1
|
| 9 |
+
- unalignment/spicy-3.1
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
The pr iestess of Athena.
|
| 13 |
+
|
| 14 |
+
Fine-tuned on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1), [my team](https://huggingface.co/ConvexAI) and I reformatted many different datasets and included a small amount of private stuff to see how much we could improve mistral.
|
| 15 |
+
|
| 16 |
+
I spoke to it personally for about an hour, and I believe we need to work on our format for the private dataset a bit more, but other than that, it turned out great. I will be uploading it to open llm evaluations, today.
|