Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,14 @@ tags:
|
|
| 10 |
pipeline_tag: translation
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
pipeline_tag: translation
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# LLaMA 2 7B - Toxicator RU
|
| 14 |
+
|
| 15 |
+
This fine-tuned model based on [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), it utilizes [evilfreelancer/toxicator-ru](https://huggingface.co/datasets/evilfreelancer/toxicator-ru) dataset created from samples in [s-nlp/russe_detox_2022](https://github.com/s-nlp/russe_detox_2022) project.
|
| 16 |
+
|
| 17 |
+
Model was tuned **just for lulz** for experimenting with [TorchTune](https://github.com/pytorch/torchtune) tool.
|
| 18 |
+
|
| 19 |
+
## Links
|
| 20 |
+
|
| 21 |
+
* https://github.com/EvilFreelancer/toxicator-ru - GitHub repository with train scripts and scripts for generating dataset
|
| 22 |
+
* https://huggingface.co/datasets/evilfreelancer/toxicator-ru - dataset
|
| 23 |
+
* https://api.wandb.ai/links/evilfreelancer/33t8pqze - wandb report about training
|