Link to live Gradio demo Space
Browse files
README.md
CHANGED
|
@@ -22,6 +22,14 @@ treatment recommendations.
|
|
| 22 |
Trained on a single **AMD Instinct MI300X** using PyTorch + ROCm, as a submission to the
|
| 23 |
lablab.ai AMD hackathon **Track 3 — Building AI-Powered Applications on AMD GPUs**.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
## Results
|
| 26 |
|
| 27 |
| Epoch | Train Loss | Val Loss | Throughput | Wall Time |
|
|
|
|
| 22 |
Trained on a single **AMD Instinct MI300X** using PyTorch + ROCm, as a submission to the
|
| 23 |
lablab.ai AMD hackathon **Track 3 — Building AI-Powered Applications on AMD GPUs**.
|
| 24 |
|
| 25 |
+
## 🌱 Try the live demo
|
| 26 |
+
|
| 27 |
+
This adapter powers the conversational layer of an interactive Plant Disease Assistant — upload a leaf photo to get a diagnosis and treatment guide:
|
| 28 |
+
|
| 29 |
+
**👉 [huggingface.co/spaces/lablab-ai-amd-developer-hackathon/merolav-space](https://huggingface.co/spaces/lablab-ai-amd-developer-hackathon/merolav-space)**
|
| 30 |
+
|
| 31 |
+
(The hosted Space runs the lighter DINOv2-L classifier on free CPU. Load this LoRA adapter on a GPU machine for the full conversational VLM experience — see the code under [`vision/`](https://github.com/genyarko/amd-merolav/tree/main/vision) in the training repo.)
|
| 32 |
+
|
| 33 |
## Results
|
| 34 |
|
| 35 |
| Epoch | Train Loss | Val Loss | Throughput | Wall Time |
|