Add model cards for val_holdout (batch 1, final)
Browse files
val_holdout/model_idx_4250/README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-to-image
|
| 5 |
+
tags:
|
| 6 |
+
- probex
|
| 7 |
+
- model-j
|
| 8 |
+
- weight-space-learning
|
| 9 |
+
- lora
|
| 10 |
+
- stable-diffusion
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model-J: SD_1k - model_idx_4250
|
| 14 |
+
|
| 15 |
+
This model is part of the **Model-J** dataset, introduced in:
|
| 16 |
+
|
| 17 |
+
**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
|
| 18 |
+
|
| 19 |
+
<p align="center">
|
| 20 |
+
🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
|
| 21 |
+
</p>
|
| 22 |
+
|
| 23 |
+
## Model Details
|
| 24 |
+
|
| 25 |
+
| Attribute | Value |
|
| 26 |
+
|---|---|
|
| 27 |
+
| **Subset** | SD_1k |
|
| 28 |
+
| **Split** | val_holdout |
|
| 29 |
+
| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
|
| 30 |
+
| **ImageNet Class** | coffee_mug (n03063599) |
|
| 31 |
+
|
| 32 |
+
## Training Hyperparameters
|
| 33 |
+
|
| 34 |
+
| Parameter | Value |
|
| 35 |
+
|---|---|
|
| 36 |
+
| Learning Rate | 3e-05 |
|
| 37 |
+
| Max Train Steps | 450 |
|
| 38 |
+
| LoRA Rank | 16 |
|
| 39 |
+
| Seed | 67 |
|
| 40 |
+
| N Training Samples | 9 |
|
val_holdout/model_idx_4251/README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: CompVis/stable-diffusion-v1-3
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-to-image
|
| 5 |
+
tags:
|
| 6 |
+
- probex
|
| 7 |
+
- model-j
|
| 8 |
+
- weight-space-learning
|
| 9 |
+
- lora
|
| 10 |
+
- stable-diffusion
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model-J: SD_1k - model_idx_4251
|
| 14 |
+
|
| 15 |
+
This model is part of the **Model-J** dataset, introduced in:
|
| 16 |
+
|
| 17 |
+
**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
|
| 18 |
+
|
| 19 |
+
<p align="center">
|
| 20 |
+
🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
|
| 21 |
+
</p>
|
| 22 |
+
|
| 23 |
+
## Model Details
|
| 24 |
+
|
| 25 |
+
| Attribute | Value |
|
| 26 |
+
|---|---|
|
| 27 |
+
| **Subset** | SD_1k |
|
| 28 |
+
| **Split** | val_holdout |
|
| 29 |
+
| **Base Model** | `CompVis/stable-diffusion-v1-3` |
|
| 30 |
+
| **ImageNet Class** | hare (n02326432) |
|
| 31 |
+
|
| 32 |
+
## Training Hyperparameters
|
| 33 |
+
|
| 34 |
+
| Parameter | Value |
|
| 35 |
+
|---|---|
|
| 36 |
+
| Learning Rate | 0.0001 |
|
| 37 |
+
| Max Train Steps | 600 |
|
| 38 |
+
| LoRA Rank | 16 |
|
| 39 |
+
| Seed | 96 |
|
| 40 |
+
| N Training Samples | 10 |
|