Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- tiiuae/falcon-refinedweb
|
|
|
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
---
|
|
@@ -19,7 +20,7 @@ We augment the RefinedWeb corproa with instruction-response pairs generated by o
|
|
| 19 |
|
| 20 |
To evaluate our general base model using the [lm-evaluation-harness framework](https://github.com/EleutherAI/lm-evaluation-harness)
|
| 21 |
|
| 22 |
-
1. Setup dependencies
|
| 23 |
```bash
|
| 24 |
git clone https://github.com/EleutherAI/lm-evaluation-harness
|
| 25 |
cd lm-evaluation-harness
|
|
@@ -48,6 +49,8 @@ accelerate launch -m lm_eval --model hf \
|
|
| 48 |
|
| 49 |
## Citation
|
| 50 |
If you find our work helpful, please cite us:
|
|
|
|
|
|
|
| 51 |
```bibtex
|
| 52 |
@inproceedings{
|
| 53 |
cheng2024adapting,
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- tiiuae/falcon-refinedweb
|
| 5 |
+
- instruction-pretrain/ft-instruction-synthesizer-collection
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
---
|
|
|
|
| 20 |
|
| 21 |
To evaluate our general base model using the [lm-evaluation-harness framework](https://github.com/EleutherAI/lm-evaluation-harness)
|
| 22 |
|
| 23 |
+
1. Setup dependencies
|
| 24 |
```bash
|
| 25 |
git clone https://github.com/EleutherAI/lm-evaluation-harness
|
| 26 |
cd lm-evaluation-harness
|
|
|
|
| 49 |
|
| 50 |
## Citation
|
| 51 |
If you find our work helpful, please cite us:
|
| 52 |
+
|
| 53 |
+
[AdaptLLM](https://huggingface.co/papers/2309.09530):
|
| 54 |
```bibtex
|
| 55 |
@inproceedings{
|
| 56 |
cheng2024adapting,
|