Add Github link, set proper license
Browse filesThis PR adds the Github repository link and sets the proper license according to the Github README.
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
@@ -19,6 +19,8 @@ This model is based on the paper [GuardReasoner: Towards Reasoning-based LLM Saf
|
|
19 |
|
20 |
The training data of R-SFT can be found in [GuardReasonerTrain](https://huggingface.co/datasets/yueliu1999/GuardReasonerTrain).
|
21 |
|
|
|
|
|
22 |
# Usage
|
23 |
```
|
24 |
import re
|
@@ -68,7 +70,6 @@ Mark
|
|
68 |
output = post_process(generate(vllm_model, prompt_list, response_list)[0].outputs[0].text)
|
69 |
|
70 |
print(output)
|
71 |
-
|
72 |
```
|
73 |
|
74 |
# Citation
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
base_model: meta-llama/Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
19 |
|
20 |
The training data of R-SFT can be found in [GuardReasonerTrain](https://huggingface.co/datasets/yueliu1999/GuardReasonerTrain).
|
21 |
|
22 |
+
Code can be found at: https://github.com/yueliu1999/GuardReasoner/.
|
23 |
+
|
24 |
# Usage
|
25 |
```
|
26 |
import re
|
|
|
70 |
output = post_process(generate(vllm_model, prompt_list, response_list)[0].outputs[0].text)
|
71 |
|
72 |
print(output)
|
|
|
73 |
```
|
74 |
|
75 |
# Citation
|