Update README.md
Browse files
README.md
CHANGED
|
@@ -27,10 +27,6 @@ output = generator([{"role": "user", "content": question}], max_new_tokens=128,
|
|
| 27 |
print(output["generated_text"])
|
| 28 |
```
|
| 29 |
|
| 30 |
-
## Training procedure
|
| 31 |
-
|
| 32 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/khalidalt/huggingface/runs/9n1ggtzj)
|
| 33 |
-
|
| 34 |
|
| 35 |
This model was trained with SFT.
|
| 36 |
|
|
@@ -44,7 +40,17 @@ This model was trained with SFT.
|
|
| 44 |
|
| 45 |
## Citations
|
| 46 |
|
|
|
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
Cite TRL as:
|
| 50 |
|
|
|
|
| 27 |
print(output["generated_text"])
|
| 28 |
```
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
This model was trained with SFT.
|
| 32 |
|
|
|
|
| 40 |
|
| 41 |
## Citations
|
| 42 |
|
| 43 |
+
Cite open-r1 as:
|
| 44 |
|
| 45 |
+
```bibtex
|
| 46 |
+
@misc{open-r1,
|
| 47 |
+
title = {{Open R1: A fully open reproduction of DeepSeek-R1.}},
|
| 48 |
+
year = 2025,
|
| 49 |
+
journal = {GitHub repository},
|
| 50 |
+
publisher = {GitHub},
|
| 51 |
+
howpublished = {\url{https://github.com/huggingface/open-r1}}
|
| 52 |
+
}
|
| 53 |
+
```
|
| 54 |
|
| 55 |
Cite TRL as:
|
| 56 |
|