Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- gpt
|
| 4 |
+
- from-scratch
|
| 5 |
+
- code-generation
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# gpt-python-124m
|
| 9 |
+
|
| 10 |
+
A ~124M parameter GPT-2-style decoder-only transformer, trained from scratch on the
|
| 11 |
+
[devoppro/Python](https://huggingface.co/datasets/devoppro/Python) dataset.
|
| 12 |
+
|
| 13 |
+
- Layers: 12
|
| 14 |
+
- Heads: 12
|
| 15 |
+
- Embedding dim: 768
|
| 16 |
+
- Context length: 512
|
| 17 |
+
- Trained to step 0, val loss 10.3904
|
| 18 |
+
- Tokenizer: GPT-2 BPE (tiktoken 'gpt2')
|