Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,64 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- argilla/ultrafeedback-binarized-preferences-cleaned
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
---
|
| 8 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 9 |
+
Trying to see the effects of DPO for own study.
|
| 10 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 11 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 12 |
+
Trying to see the effects of DPO for own study.
|
| 13 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 14 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 15 |
+
Trying to see the effects of DPO for own study.
|
| 16 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 17 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 18 |
+
Trying to see the effects of DPO for own study.
|
| 19 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 20 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 21 |
+
Trying to see the effects of DPO for own study.
|
| 22 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 23 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 24 |
+
Trying to see the effects of DPO for own study.
|
| 25 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 26 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 27 |
+
Trying to see the effects of DPO for own study.
|
| 28 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 29 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 30 |
+
Trying to see the effects of DPO for own study.
|
| 31 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
|
| 32 |
+
Trying to see the effects of DPO for own study.
|
| 33 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 34 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 35 |
+
Trying to see the effects of DPO for own study.
|
| 36 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 37 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 38 |
+
Trying to see the effects of DPO for own study.
|
| 39 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 40 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 41 |
+
Trying to see the effects of DPO for own study.
|
| 42 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
|
| 43 |
+
Trying to see the effects of DPO for own study.
|
| 44 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 45 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 46 |
+
Trying to see the effects of DPO for own study.
|
| 47 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 48 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 49 |
+
Trying to see the effects of DPO for own study.
|
| 50 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 51 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 52 |
+
Trying to see the effects of DPO for own study.
|
| 53 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performanceTesting Mistral-Instruct model with Orca DPO dataset.
|
| 54 |
+
Trying to see the effects of DPO for own study.
|
| 55 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 56 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 57 |
+
Trying to see the effects of DPO for own study.
|
| 58 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 59 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 60 |
+
Trying to see the effects of DPO for own study.
|
| 61 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|
| 62 |
+
Testing Mistral-Instruct model with Orca DPO dataset.
|
| 63 |
+
Trying to see the effects of DPO for own study.
|
| 64 |
+
Used Mistral-7B-Instrcut-v0.2 model due to its good performance
|