12sciencejnv
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,6 @@ new_version: openai-community/gpt2
|
|
16 |
---
|
17 |
|
18 |
# ChadGPT
|
19 |
-
|
20 |
This model is a fine-tuned version of GPT-2 on the `minhalvp/islamqa` dataset, which consists of Islamic question-answer pairs. It is designed for generating answers to Islamic questions.
|
21 |
|
22 |
## License
|
@@ -29,13 +28,14 @@ The model is fine-tuned on the `minhalvp/islamqa` dataset from Hugging Face.
|
|
29 |
English
|
30 |
|
31 |
## Metrics
|
32 |
-
-
|
|
|
33 |
|
34 |
## Base Model
|
35 |
The model is based on the `gpt2` architecture.
|
36 |
|
37 |
## New Version
|
38 |
-
|
39 |
|
40 |
## Pipeline Tag
|
41 |
text-generation
|
|
|
16 |
---
|
17 |
|
18 |
# ChadGPT
|
|
|
19 |
This model is a fine-tuned version of GPT-2 on the `minhalvp/islamqa` dataset, which consists of Islamic question-answer pairs. It is designed for generating answers to Islamic questions.
|
20 |
|
21 |
## License
|
|
|
28 |
English
|
29 |
|
30 |
## Metrics
|
31 |
+
- **Perplexity**: 170.31 (calculated on the validation set of the minhalvp/islamqa dataset)
|
32 |
+
- **Training Loss**: 2.3 (final training loss after fine-tuning)
|
33 |
|
34 |
## Base Model
|
35 |
The model is based on the `gpt2` architecture.
|
36 |
|
37 |
## New Version
|
38 |
+
gpt2 (Base model, fine-tuned version)
|
39 |
|
40 |
## Pipeline Tag
|
41 |
text-generation
|