Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
- agent
|
| 13 |
---
|
| 14 |
|
| 15 |
-
QLoRA adaptor for [allenai/Molmo-7B-D-0924](https://huggingface.co/allenai/Molmo-7B-D-0924),
|
| 16 |
|
| 17 |
Targets attention layer of Transformer backbone and image pooling and projection layers of Vision backbone
|
| 18 |
|
|
@@ -20,4 +20,11 @@ Trained on 47 screenshots of a low-poly video game with ragdoll casualties
|
|
| 20 |
|
| 21 |
Evaluated on 44 screenshots of aforementioned video game
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
Dataset: [reubk/RavenfieldDataset](https://huggingface.co/datasets/reubk/RavenfieldDataset)
|
|
|
|
| 12 |
- agent
|
| 13 |
---
|
| 14 |
|
| 15 |
+
Testing a QLoRA adaptor for [allenai/Molmo-7B-D-0924](https://huggingface.co/allenai/Molmo-7B-D-0924),
|
| 16 |
|
| 17 |
Targets attention layer of Transformer backbone and image pooling and projection layers of Vision backbone
|
| 18 |
|
|
|
|
| 20 |
|
| 21 |
Evaluated on 44 screenshots of aforementioned video game
|
| 22 |
|
| 23 |
+
Comparison of Model performance with and without QLora on Eval dataset
|
| 24 |
+
|Model| Molmo-7B-D | Molmo-7B-D w/ QLora |
|
| 25 |
+
|----------|------|------|
|
| 26 |
+
| Accuracy | 70.4 | 87.9 |
|
| 27 |
+
| Precision | 92.1 | 80.3 |
|
| 28 |
+
| Recall | 70.4 | 89.7 |
|
| 29 |
+
|
| 30 |
Dataset: [reubk/RavenfieldDataset](https://huggingface.co/datasets/reubk/RavenfieldDataset)
|