Tweak README and open PR
#1
by McClain - opened
README.md
CHANGED
|
@@ -44,3 +44,8 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
| 44 |
Notes:
|
| 45 |
- Use sampling (`temperature`, `top_p`) for diverse sequences; disable sampling for deterministic outputs.
|
| 46 |
- Runs on CPU, CUDA, or Apple MPS depending on your PyTorch installation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
Notes:
|
| 45 |
- Use sampling (`temperature`, `top_p`) for diverse sequences; disable sampling for deterministic outputs.
|
| 46 |
- Runs on CPU, CUDA, or Apple MPS depending on your PyTorch installation.
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
Changelog:
|
| 50 |
+
- Update weights to checkpoint-2300
|
| 51 |
+
- Simplify README and add W&B run link
|