Add model cards for val_holdout (batch 3)

val_holdout/model_idx_4350/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4350
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Bouvier_des_Flandres (n02106382) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 33 |
+| N Training Samples | 6 |

val_holdout/model_idx_4351/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4351
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 80 |
+| N Training Samples | 5 |

val_holdout/model_idx_4352/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4352
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 68 |
+| N Training Samples | 5 |

val_holdout/model_idx_4353/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4353
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | papillon (n02086910) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 6 |
+| N Training Samples | 10 |

val_holdout/model_idx_4354/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4354
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 41 |
+| N Training Samples | 10 |

val_holdout/model_idx_4355/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4355
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | groenendael (n02105056) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 47 |
+| N Training Samples | 5 |

val_holdout/model_idx_4356/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4356
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Siamese_cat (n02123597) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 13 |
+| N Training Samples | 5 |

val_holdout/model_idx_4357/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4357
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 21 |
+| N Training Samples | 5 |

val_holdout/model_idx_4358/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4358
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 62 |
+| N Training Samples | 9 |

val_holdout/model_idx_4359/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4359
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Leonberg (n02111129) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 39 |
+| N Training Samples | 7 |

val_holdout/model_idx_4360/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4360
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 17 |
+| N Training Samples | 7 |

val_holdout/model_idx_4361/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4361
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | hyena (n02117135) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 9 |

val_holdout/model_idx_4362/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4362
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 88 |
+| N Training Samples | 5 |

val_holdout/model_idx_4363/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4363
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 72 |
+| N Training Samples | 9 |

val_holdout/model_idx_4364/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4364
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | polecat (n02443114) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 28 |
+| N Training Samples | 10 |

val_holdout/model_idx_4365/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4365
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Pembroke (n02113023) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 83 |
+| N Training Samples | 8 |

val_holdout/model_idx_4366/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4366
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 48 |
+| N Training Samples | 8 |

val_holdout/model_idx_4367/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4367
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | hyena (n02117135) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 46 |
+| N Training Samples | 6 |

val_holdout/model_idx_4368/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4368
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | chow (n02112137) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 74 |
+| N Training Samples | 6 |

val_holdout/model_idx_4369/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4369
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Siamese_cat (n02123597) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 20 |
+| N Training Samples | 6 |

val_holdout/model_idx_4370/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4370
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Siamese_cat (n02123597) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 58 |
+| N Training Samples | 5 |

val_holdout/model_idx_4371/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4371
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Scotch_terrier (n02097298) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 7 |

val_holdout/model_idx_4372/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4372
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 28 |
+| N Training Samples | 8 |

val_holdout/model_idx_4373/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4373
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 36 |
+| N Training Samples | 6 |

val_holdout/model_idx_4374/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4374
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Siamese_cat (n02123597) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 18 |
+| N Training Samples | 10 |

val_holdout/model_idx_4375/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4375
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 47 |
+| N Training Samples | 6 |

val_holdout/model_idx_4376/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4376
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 62 |
+| N Training Samples | 9 |

val_holdout/model_idx_4377/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4377
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Siamese_cat (n02123597) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 81 |
+| N Training Samples | 10 |

val_holdout/model_idx_4378/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4378
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 77 |
+| N Training Samples | 7 |

val_holdout/model_idx_4379/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4379
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Rottweiler (n02106550) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 43 |
+| N Training Samples | 6 |

val_holdout/model_idx_4380/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4380
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Sussex_spaniel (n02102480) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 99 |
+| N Training Samples | 5 |

val_holdout/model_idx_4381/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4381
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Rottweiler (n02106550) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 77 |
+| N Training Samples | 7 |

val_holdout/model_idx_4382/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4382
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Leonberg (n02111129) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 9 |

val_holdout/model_idx_4383/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4383
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | hyena (n02117135) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 24 |
+| N Training Samples | 8 |

val_holdout/model_idx_4384/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4384
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Leonberg (n02111129) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 61 |
+| N Training Samples | 9 |

val_holdout/model_idx_4385/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4385
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Bouvier_des_Flandres (n02106382) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 37 |
+| N Training Samples | 7 |

val_holdout/model_idx_4386/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4386
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 8 |

val_holdout/model_idx_4387/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4387
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 3 |
+| N Training Samples | 6 |

val_holdout/model_idx_4388/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4388
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 8 |
+| N Training Samples | 6 |

val_holdout/model_idx_4389/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4389
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 2 |
+| N Training Samples | 8 |

val_holdout/model_idx_4390/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-4
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4390
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 71 |
+| N Training Samples | 9 |

val_holdout/model_idx_4391/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4391
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 9 |

val_holdout/model_idx_4392/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4392
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Bouvier_des_Flandres (n02106382) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 99 |
+| N Training Samples | 8 |

val_holdout/model_idx_4393/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4393
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Persian_cat (n02123394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 41 |
+| N Training Samples | 7 |

val_holdout/model_idx_4394/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4394
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | capuchin (n02492035) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 66 |
+| N Training Samples | 6 |

val_holdout/model_idx_4395/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4395
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | boxer (n02108089) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 52 |
+| N Training Samples | 7 |

val_holdout/model_idx_4396/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-2
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4396
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 45 |
+| N Training Samples | 10 |

val_holdout/model_idx_4397/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4397
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 5 |

val_holdout/model_idx_4398/README.md

@@ -0,0 +1,40 @@
+---
+base_model: CompVis/stable-diffusion-v1-3
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4398
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | impala (n02422699) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 20 |
+| N Training Samples | 6 |

val_holdout/model_idx_4399/README.md

@@ -0,0 +1,40 @@
+---
+base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
+library_name: peft
+pipeline_tag: text-to-image
+tags:
+  - probex
+  - model-j
+  - weight-space-learning
+  - lora
+  - stable-diffusion
+---
+
+# Model-J: SD_200 - model_idx_4399
+
+This model is part of the **Model-J** dataset, introduced in:
+
+**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
+
+<p align="center">
+    🌐 <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>
+</p>
+
+## Model Details
+
+| Attribute | Value |
+|---|---|
+| **Subset** | SD_200 |
+| **Split** | val_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | chow (n02112137) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 33 |
+| N Training Samples | 5 |