Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ datasets:
|
|
| 7 |
|
| 8 |
# Configurable-LLama-3-8B
|
| 9 |
|
|
|
|
|
|
|
| 10 |
A configurable Llama-3 fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495, over the
|
| 11 |
[vicgalle/configurable-system-prompt-multitask](https://huggingface.co/datasets/vicgalle/configurable-system-prompt-multitask) dataset.
|
| 12 |
|
|
|
|
| 7 |
|
| 8 |
# Configurable-LLama-3-8B
|
| 9 |
|
| 10 |
+
❗️ New version of the model at https://huggingface.co/vicgalle/Configurable-Llama-3-8B-v0.3. You'll almost always want to use that one, as it fixes the tokenization isse discussed at the end of this model card.
|
| 11 |
+
|
| 12 |
A configurable Llama-3 fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495, over the
|
| 13 |
[vicgalle/configurable-system-prompt-multitask](https://huggingface.co/datasets/vicgalle/configurable-system-prompt-multitask) dataset.
|
| 14 |
|