Update README.md
Browse files
README.md
CHANGED
@@ -40,6 +40,8 @@ widget:
|
|
40 |
|
41 |
# bart-base-instructiongen
|
42 |
|
|
|
|
|
43 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the pszemraj/fleece2instructions dataset.
|
44 |
It achieves the following results on the evaluation set:
|
45 |
- Loss: 1.0034
|
@@ -49,13 +51,9 @@ It achieves the following results on the evaluation set:
|
|
49 |
- Rougelsum: 59.8931
|
50 |
- Gen Len: 14.3179
|
51 |
|
52 |
-
## Model description
|
53 |
-
|
54 |
-
More information needed
|
55 |
-
|
56 |
## Intended uses & limitations
|
57 |
|
58 |
-
|
59 |
|
60 |
## Training and evaluation data
|
61 |
|
|
|
40 |
|
41 |
# bart-base-instructiongen
|
42 |
|
43 |
+
Instead of generating questions from text, generate instructions for LLMs!
|
44 |
+
|
45 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the pszemraj/fleece2instructions dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
- Loss: 1.0034
|
|
|
51 |
- Rougelsum: 59.8931
|
52 |
- Gen Len: 14.3179
|
53 |
|
|
|
|
|
|
|
|
|
54 |
## Intended uses & limitations
|
55 |
|
56 |
+
This is just a base model/example, and there is likely even better performance with larger models.
|
57 |
|
58 |
## Training and evaluation data
|
59 |
|