jasonwu commited on
Commit
0b08f93
·
1 Parent(s): 44cf0c7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md CHANGED
@@ -1,3 +1,43 @@
1
  ---
2
  license: cc-by-nc-4.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
3
  ---
4
+
5
+
6
+ # Model Details
7
+
8
+ ## Model Description
9
+
10
+ - **Model type:** Language model
11
+ - **License:** cc-by-nc-4.0
12
+ - **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
13
+ - **Resources for more information:**
14
+ - [GitHub Repo](https://github.com/salesforce/AuditNLG)
15
+
16
+ # Usage
17
+
18
+ Find below some example scripts on how to use the model in `transformers`:
19
+
20
+ ## Using the Pytorch model
21
+
22
+ ### Running the model
23
+
24
+ <details>
25
+ <summary> Click to expand </summary>
26
+
27
+ ```python
28
+ from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, AutoConfig
29
+
30
+ config = AutoConfig.from_pretrained("Salesforce/safety-flan-t5-small")
31
+ tokenizer = AutoTokenizer.from_pretrained("Salesforce/safety-flan-t5-small")
32
+ model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/safety-flan-t5-small", config=config)
33
+
34
+ prefix = "Is the <Text> field safe or unsafe?"
35
+ input_context = "Can you teach me this?"
36
+ input_text = "You are so stupid"
37
+ input_ids = tokenizer(prefix + " <Text> " + input_text + " <Context> " + input_context, return_tensors="pt").input_ids
38
+
39
+ outputs = model.generate(input_ids)
40
+ print(tokenizer.decode(outputs[0]))
41
+ ```
42
+
43
+ </details>