Update README.md
Browse files
README.md
CHANGED
|
@@ -22,27 +22,17 @@ widget:
|
|
| 22 |
pipeline_tag: text-generation
|
| 23 |
---
|
| 24 |
|
| 25 |
-
|
| 26 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
|
| 28 |
-
|
|
|
|
|
|
|
| 29 |
|
| 30 |
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA) on the None dataset.
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
- Loss: 2.8431
|
| 33 |
- Accuracy: 0.4682
|
| 34 |
|
| 35 |
-
## Model description
|
| 36 |
-
|
| 37 |
-
More information needed
|
| 38 |
-
|
| 39 |
-
## Intended uses & limitations
|
| 40 |
-
|
| 41 |
-
More information needed
|
| 42 |
-
|
| 43 |
-
## Training and evaluation data
|
| 44 |
-
|
| 45 |
-
More information needed
|
| 46 |
|
| 47 |
## Training procedure
|
| 48 |
|
|
|
|
| 22 |
pipeline_tag: text-generation
|
| 23 |
---
|
| 24 |
|
| 25 |
+
# smol_llama-101M-midjourney-messages
|
|
|
|
| 26 |
|
| 27 |
+
Given a 'partial prompt' for a text2image model, this generates additional relevant text to include for a full prompt.
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
|
| 31 |
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA) on the None dataset.
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
- Loss: 2.8431
|
| 34 |
- Accuracy: 0.4682
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
## Training procedure
|
| 38 |
|