Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,10 @@ language:
|
|
| 15 |
> [!IMPORTANT]
|
| 16 |
> this was finetuned at 16384 context length
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
This model is a fine-tuned version of [Qwen/Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) on https://github.com/stepbasin/books/tree/master/books
|
| 19 |
|
| 20 |
It achieves the following results on the evaluation set:
|
|
|
|
| 15 |
> [!IMPORTANT]
|
| 16 |
> this was finetuned at 16384 context length
|
| 17 |
|
| 18 |
+
This is an experiment on long-context text **generation** (i.e. 6k+ tokens) generated to evaluate if/when generation falls apart, etc. As such, all of the data this model was fine-tuned on are full-length books.
|
| 19 |
+
|
| 20 |
+
## Details
|
| 21 |
+
|
| 22 |
This model is a fine-tuned version of [Qwen/Qwen2-1.5B](https://huggingface.co/Qwen/Qwen2-1.5B) on https://github.com/stepbasin/books/tree/master/books
|
| 23 |
|
| 24 |
It achieves the following results on the evaluation set:
|