Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@ LilLM 39M parameter model fine-tuned on SFT dataset.
|
|
| 2 |
|
| 3 |
The dataset only includes examples with sequence length < 512 (according to our own tokenizer)
|
| 4 |
|
| 5 |
-
Find the SFT dataset here: https://huggingface.co/datasets/CohleM/lillm-sft-dataset-512
|
| 6 |
Find the data-preparation file here: https://colab.research.google.com/drive/1QkIpkhaZVNvZwBoD69N5O-md5FjRSW_W
|
| 7 |
|
| 8 |
|
|
|
|
| 2 |
|
| 3 |
The dataset only includes examples with sequence length < 512 (according to our own tokenizer)
|
| 4 |
|
| 5 |
+
Find the SFT dataset here: https://huggingface.co/datasets/CohleM/lillm-sft-dataset-512-including-hard-coded-mixture
|
| 6 |
Find the data-preparation file here: https://colab.research.google.com/drive/1QkIpkhaZVNvZwBoD69N5O-md5FjRSW_W
|
| 7 |
|
| 8 |
|