Commit
•
694c35d
1
Parent(s):
c62cf90
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,8 @@ OpenCerebrum-1.0-7B-DPO is an open-source language model fine-tuned from the alp
|
|
| 21 |
|
| 22 |
The model was fine-tuned on approximately 21,000 examples across 6 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels.
|
| 23 |
|
|
|
|
|
|
|
| 24 |
## Model Details
|
| 25 |
|
| 26 |
- **Base Model:** alpindale/Mistral-7B-v0.2-hf
|
|
|
|
| 21 |
|
| 22 |
The model was fine-tuned on approximately 21,000 examples across 6 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels.
|
| 23 |
|
| 24 |
+
I used the ChatML prompt format to train this model.
|
| 25 |
+
|
| 26 |
## Model Details
|
| 27 |
|
| 28 |
- **Base Model:** alpindale/Mistral-7B-v0.2-hf
|