Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,16 @@ Trained using 10GB of USENET posts along with over 1 GB of miscellaneous BBS pos
|
|
| 14 |
This model has 10 layers, 10 heads and 640 embeddings, with a context window of 1024 tokens.
|
| 15 |
Supervised fine-tuning should be performed before use.
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Training Information
|
| 18 |
| | |
|
| 19 |
|---------------------------------|----:|
|
|
@@ -22,6 +32,7 @@ Supervised fine-tuning should be performed before use.
|
|
| 22 |
|Device |Google Colab L4|
|
| 23 |
|Training Time |16 Hours|
|
| 24 |
|
|
|
|
| 25 |
## Syntax
|
| 26 |
```
|
| 27 |
uucp:
|
|
|
|
| 14 |
This model has 10 layers, 10 heads and 640 embeddings, with a context window of 1024 tokens.
|
| 15 |
Supervised fine-tuning should be performed before use.
|
| 16 |
|
| 17 |
+
## Technical Information
|
| 18 |
+
| | |
|
| 19 |
+
|---------------------------------|----:|
|
| 20 |
+
|Layers |10|
|
| 21 |
+
|Heads |10|
|
| 22 |
+
|Embeddings |640|
|
| 23 |
+
|Context Window |1024 tokens|
|
| 24 |
+
|Tokenizer |GPT-2 BPE|
|
| 25 |
+
|
| 26 |
+
|
| 27 |
## Training Information
|
| 28 |
| | |
|
| 29 |
|---------------------------------|----:|
|
|
|
|
| 32 |
|Device |Google Colab L4|
|
| 33 |
|Training Time |16 Hours|
|
| 34 |
|
| 35 |
+
|
| 36 |
## Syntax
|
| 37 |
```
|
| 38 |
uucp:
|