Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,42 @@
|
|
1 |
---
|
2 |
{}
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
{}
|
3 |
+
---
|
4 |
+
|
5 |
+
# Model Details
|
6 |
+
|
7 |
+
## Model Description
|
8 |
+
|
9 |
+
- **Model type:** Language model
|
10 |
+
- **License:** CC BY-NC
|
11 |
+
- **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
|
12 |
+
- **Resources for more information:**
|
13 |
+
- [GitHub Repo](https://github.com/salesforce/AuditNLG)
|
14 |
+
|
15 |
+
# Usage
|
16 |
+
|
17 |
+
Find below some example scripts on how to use the model in `transformers`:
|
18 |
+
|
19 |
+
## Using the Pytorch model
|
20 |
+
|
21 |
+
### Running the model
|
22 |
+
|
23 |
+
<details>
|
24 |
+
<summary> Click to expand </summary>
|
25 |
+
|
26 |
+
```python
|
27 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, AutoConfig
|
28 |
+
|
29 |
+
config = AutoConfig.from_pretrained("Salesforce/safety-flan-t5-base")
|
30 |
+
tokenizer = AutoTokenizer.from_pretrained("Salesforce/safety-flan-t5-base")
|
31 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/safety-flan-t5-base", config=config)
|
32 |
+
|
33 |
+
prefix = "Is the <Text> field safe or unsafe?"
|
34 |
+
input_context = "Can you teach me this?"
|
35 |
+
input_text = "You are so stupid"
|
36 |
+
input_ids = tokenizer(prefix + " <Text> " + input_text + " <Context> " + input_context, return_tensors="pt").input_ids
|
37 |
+
|
38 |
+
outputs = model.generate(input_ids)
|
39 |
+
print(tokenizer.decode(outputs[0]))
|
40 |
+
```
|
41 |
+
|
42 |
+
</details>
|