Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -4,11 +4,12 @@ datasets:
|
|
| 4 |
- normster/RealGuardrails
|
| 5 |
base_model:
|
| 6 |
- meta-llama/Llama-3.2-3B
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# RealGuardrails Models
|
| 10 |
|
| 11 |
-
This model was trained on the [RealGuardrails](https://huggingface.co/datasets/normster/RealGuardrails) dataset, an instruction-tuning dataset focused on improving system prompt adherence and precedence. In particular, it was trained via SFT on the `systemmix` split of ~150K examples using our custom training library [torchllms](https://github.com/normster/torchllms).
|
| 12 |
|
| 13 |
## Training Hyperparameters
|
| 14 |
|
|
|
|
| 4 |
- normster/RealGuardrails
|
| 5 |
base_model:
|
| 6 |
- meta-llama/Llama-3.2-3B
|
| 7 |
+
library_name: transformers
|
| 8 |
---
|
| 9 |
|
| 10 |
# RealGuardrails Models
|
| 11 |
|
| 12 |
+
This model was trained on the [RealGuardrails](https://huggingface.co/datasets/normster/RealGuardrails) dataset, an instruction-tuning dataset focused on improving system prompt adherence and precedence. In particular, it was trained via SFT on the `systemmix` split of ~150K examples using our custom training library [torchllms](https://github.com/normster/torchllms) and converted back to a `transformers` compatible checkpoint.
|
| 13 |
|
| 14 |
## Training Hyperparameters
|
| 15 |
|