Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
## Dataset
|
| 5 |
+
Collection of William Shakespeare plays
|
| 6 |
+
- tiktoken - gpt2 tokenizer is used for tokenization
|
| 7 |
+
- Number of total tokens - 338025
|
| 8 |
+
|
| 9 |
+
## The HuggingFace Spaces Gradio App
|
| 10 |
+
|
| 11 |
+
The app is available [here](https://huggingface.co/spaces/sayanbanerjee32/nanogpt2_text_generator)
|
| 12 |
+
|
| 13 |
+
The App takes following as input
|
| 14 |
+
1. Seed Text (Prompt) - This is provided as input text to the GPT model, based on which it generates further contents. If no data is provided, the only a space (" ") is provided as input
|
| 15 |
+
2. Max tokens to generate - This controls the numbers of tokens it will generate. The default value is 100.
|
| 16 |
+
3. Temperature - This accepts values between 0 to 1. Higher value introduces more randomness in the next token generation. Default value is set to 0.7.
|
| 17 |
+
4. Select Top N in each step - This is an optional field. If no value is provided (or <= 0), all available tokens are considered for the next token prediction based on SoftMax probability. However, if a number is set then only that many top tokes will be considered for the next token prediction.
|