Update README.md
Browse files
README.md
CHANGED
|
@@ -7,15 +7,11 @@ tags:
|
|
| 7 |
- GPT-4
|
| 8 |
- GPT
|
| 9 |
---
|
| 10 |
-
|
| 11 |
|
| 12 |
-
|
| 13 |
# GPT-sZero
|
| 14 |
-
|
| 15 |
GPT-sZero is a text generation model meant to answer the question: "How strong of a model can Google Colab create?"
|
| 16 |
|
| 17 |
### Model Description
|
| 18 |
-
|
| 19 |
GPT-sZero has 16 heads, 24 layers, and 1280 embeddings, similar to GPT2-Large, with a context window of 16,384 tokens. This maximized GPU VRAM while balancing size and functionality.
|
| 20 |
|
| 21 |
- **Developed by:** HDTenEightyP
|
|
@@ -24,7 +20,7 @@ GPT-sZero has 16 heads, 24 layers, and 1280 embeddings, similar to GPT2-Large, w
|
|
| 24 |
- **License:** MIT
|
| 25 |
|
| 26 |
### Model Architecture
|
| 27 |
-
|
|
| 28 |
|---------------------------------|----:|
|
| 29 |
|Layers |24|
|
| 30 |
|Heads |16|
|
|
|
|
| 7 |
- GPT-4
|
| 8 |
- GPT
|
| 9 |
---
|
|
|
|
| 10 |
|
|
|
|
| 11 |
# GPT-sZero
|
|
|
|
| 12 |
GPT-sZero is a text generation model meant to answer the question: "How strong of a model can Google Colab create?"
|
| 13 |
|
| 14 |
### Model Description
|
|
|
|
| 15 |
GPT-sZero has 16 heads, 24 layers, and 1280 embeddings, similar to GPT2-Large, with a context window of 16,384 tokens. This maximized GPU VRAM while balancing size and functionality.
|
| 16 |
|
| 17 |
- **Developed by:** HDTenEightyP
|
|
|
|
| 20 |
- **License:** MIT
|
| 21 |
|
| 22 |
### Model Architecture
|
| 23 |
+
| | |
|
| 24 |
|---------------------------------|----:|
|
| 25 |
|Layers |24|
|
| 26 |
|Heads |16|
|