Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,3 @@
|
|
| 1 |
-
<center>
|
| 2 |
-
<img src="https://huggingface.co/hamishivi/tulu-2-multitask-rrmax-326k-sft/resolve/main/image.png" alt="Practical Large-Scale Data Selection for Instruction Tuning logo" width="200px"/>
|
| 3 |
-
</center>
|
| 4 |
-
|
| 5 |
# RDS+ Multitask Tulu 2 326k
|
| 6 |
|
| 7 |
This is a model trained on 326k samples selected by RDS+ for multiple tasks at once from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).
|
|
@@ -9,6 +5,9 @@ For more details, please see the paper [Practical Large-Scale Data Selection for
|
|
| 9 |
|
| 10 |
This model outperforms the original [Tulu 2 SFT checkpoint]() by selecting more targeted data from the same original pool of data.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
## .Model description
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# RDS+ Multitask Tulu 2 326k
|
| 2 |
|
| 3 |
This is a model trained on 326k samples selected by RDS+ for multiple tasks at once from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).
|
|
|
|
| 5 |
|
| 6 |
This model outperforms the original [Tulu 2 SFT checkpoint]() by selecting more targeted data from the same original pool of data.
|
| 7 |
|
| 8 |
+
<center>
|
| 9 |
+
<img src="https://huggingface.co/hamishivi/tulu-2-multitask-rrmax-326k-sft/resolve/main/image.png" alt="Practical Large-Scale Data Selection for Instruction Tuning logo" width="200px"/>
|
| 10 |
+
</center>
|
| 11 |
|
| 12 |
## .Model description
|
| 13 |
|