k050506koch
commited on
Commit
•
9e99f4d
1
Parent(s):
c99c451
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,4 @@
|
|
1 |
-
|
2 |
-
{}
|
3 |
-
---
|
4 |
-
# Hugging Face v2 Models README & Model Card
|
5 |
|
6 |
## Overview
|
7 |
|
@@ -35,7 +32,7 @@ To use the models for inference, you can send a POST request to the `/generate/<
|
|
35 |
|
36 |
### Example Request
|
37 |
|
38 |
-
```
|
39 |
{
|
40 |
"input_text": "[Ivan Ivanov, Lead Software Engineer, Superhero for Justice, Writing code, fixing issues, solving problems, Masculine, Long Hair, Adult]<|endoftext|>"
|
41 |
}
|
@@ -47,7 +44,7 @@ To use the models for inference, you can send a POST request to the `/generate/<
|
|
47 |
|
48 |
You can load a model and its tokenizer as follows:
|
49 |
|
50 |
-
```
|
51 |
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
52 |
model_name = "v2/story/small" # Change to your desired model path
|
53 |
model = GPT2LMHeadModel.from_pretrained(model_name)
|
@@ -59,7 +56,7 @@ tokenizer = GPT2Tokenizer.from_pretrained(model_name)
|
|
59 |
|
60 |
To generate text using the loaded model, use the following code:
|
61 |
|
62 |
-
```
|
63 |
input_text = "Once upon a time"
|
64 |
input_ids = tokenizer.encode(input_text, return_tensors="pt")
|
65 |
output = model.generate(input_ids, max_length=50, do_sample=True)
|
|
|
1 |
+
# v2 Model Card
|
|
|
|
|
|
|
2 |
|
3 |
## Overview
|
4 |
|
|
|
32 |
|
33 |
### Example Request
|
34 |
|
35 |
+
```json
|
36 |
{
|
37 |
"input_text": "[Ivan Ivanov, Lead Software Engineer, Superhero for Justice, Writing code, fixing issues, solving problems, Masculine, Long Hair, Adult]<|endoftext|>"
|
38 |
}
|
|
|
44 |
|
45 |
You can load a model and its tokenizer as follows:
|
46 |
|
47 |
+
```python
|
48 |
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
49 |
model_name = "v2/story/small" # Change to your desired model path
|
50 |
model = GPT2LMHeadModel.from_pretrained(model_name)
|
|
|
56 |
|
57 |
To generate text using the loaded model, use the following code:
|
58 |
|
59 |
+
```python
|
60 |
input_text = "Once upon a time"
|
61 |
input_ids = tokenizer.encode(input_text, return_tensors="pt")
|
62 |
output = model.generate(input_ids, max_length=50, do_sample=True)
|