Add model cards for test_holdout (batch 9)

test_holdout/model_idx_4899/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_1k - model_idx_4899
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | paintbrush (n03876231) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 30 |
+| N Training Samples | 6 |

test_holdout/model_idx_4900/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_1k - model_idx_4900
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | cabbage_butterfly (n02280649) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 59 |
+| N Training Samples | 7 |

test_holdout/model_idx_4901/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_1k - model_idx_4901
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | screen (n04152593) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 97 |
+| N Training Samples | 5 |

test_holdout/model_idx_4902/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_1k - model_idx_4902
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | bannister (n02788148) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 69 |
+| N Training Samples | 8 |

test_holdout/model_idx_4903/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_1k - model_idx_4903
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | potter's_wheel (n03992509) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 10 |

test_holdout/model_idx_4904/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_1k - model_idx_4904
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Brittany_spaniel (n02101388) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 83 |
+| N Training Samples | 8 |

test_holdout/model_idx_4905/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_1k - model_idx_4905
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | streetcar (n04335435) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 72 |
+| N Training Samples | 5 |

test_holdout/model_idx_4906/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_1k - model_idx_4906
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | rocking_chair (n04099969) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 59 |
+| N Training Samples | 6 |

test_holdout/model_idx_4907/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_1k - model_idx_4907
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | oil_filter (n03843555) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 26 |
+| N Training Samples | 9 |

test_holdout/model_idx_4908/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_1k - model_idx_4908
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | toucan (n01843383) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 7 |
+| N Training Samples | 6 |

test_holdout/model_idx_4909/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_1k - model_idx_4909
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Afghan_hound (n02088094) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 9 |
+| N Training Samples | 8 |

test_holdout/model_idx_4910/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_1k - model_idx_4910
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | shield (n04192698) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 42 |
+| N Training Samples | 7 |

test_holdout/model_idx_4911/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_1k - model_idx_4911
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Granny_Smith (n07742313) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 16 |
+| N Training Samples | 6 |

test_holdout/model_idx_4912/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_1k - model_idx_4912
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | parallel_bars (n03888605) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 53 |
+| N Training Samples | 5 |

test_holdout/model_idx_4913/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_1k - model_idx_4913
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | dome (n03220513) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 94 |
+| N Training Samples | 10 |

test_holdout/model_idx_4914/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_1k - model_idx_4914
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Afghan_hound (n02088094) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 24 |
+| N Training Samples | 7 |

test_holdout/model_idx_4915/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_1k - model_idx_4915
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | pretzel (n07695742) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 6 |
+| N Training Samples | 6 |

test_holdout/model_idx_4916/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_1k - model_idx_4916
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | flamingo (n02007558) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 49 |
+| N Training Samples | 6 |

test_holdout/model_idx_4917/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_1k - model_idx_4917
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | tile_roof (n04435653) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 0 |
+| N Training Samples | 8 |

test_holdout/model_idx_4918/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_1k - model_idx_4918
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | flute (n03372029) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 60 |
+| N Training Samples | 7 |

test_holdout/model_idx_4919/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_1k - model_idx_4919
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | barrow (n02797295) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 72 |
+| N Training Samples | 6 |

test_holdout/model_idx_4920/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_1k - model_idx_4920
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | oxcart (n03868242) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 84 |
+| N Training Samples | 8 |

test_holdout/model_idx_4921/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_1k - model_idx_4921
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 91 |
+| N Training Samples | 9 |

test_holdout/model_idx_4922/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_1k - model_idx_4922
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | warthog (n02397096) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 9 |

test_holdout/model_idx_4923/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_1k - model_idx_4923
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | jeep (n03594945) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 70 |
+| N Training Samples | 6 |

test_holdout/model_idx_4924/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_1k - model_idx_4924
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | orangutan (n02480495) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 66 |
+| N Training Samples | 7 |

test_holdout/model_idx_4925/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_1k - model_idx_4925
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | wine_bottle (n04591713) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 10 |

test_holdout/model_idx_4926/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_1k - model_idx_4926
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | flamingo (n02007558) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 8 |
+| N Training Samples | 10 |

test_holdout/model_idx_4927/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_1k - model_idx_4927
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | tub (n04493381) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 85 |
+| N Training Samples | 9 |

test_holdout/model_idx_4928/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_1k - model_idx_4928
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | chiffonier (n03016953) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 50 |
+| N Training Samples | 9 |

test_holdout/model_idx_4929/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_1k - model_idx_4929
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | canoe (n02951358) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 33 |
+| N Training Samples | 8 |

test_holdout/model_idx_4930/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_1k - model_idx_4930
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | indri (n02500267) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 37 |
+| N Training Samples | 8 |

test_holdout/model_idx_4931/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_1k - model_idx_4931
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | violin (n04536866) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 10 |

test_holdout/model_idx_4932/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_1k - model_idx_4932
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | alligator_lizard (n01689811) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 31 |
+| N Training Samples | 10 |

test_holdout/model_idx_4933/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_1k - model_idx_4933
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | bell_pepper (n07720875) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 3 |
+| N Training Samples | 5 |

test_holdout/model_idx_4934/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_1k - model_idx_4934
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | brassiere (n02892767) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 27 |
+| N Training Samples | 6 |

test_holdout/model_idx_4935/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_1k - model_idx_4935
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | mouse (n03793489) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 86 |
+| N Training Samples | 7 |

test_holdout/model_idx_4936/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_1k - model_idx_4936
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | shield (n04192698) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 85 |
+| N Training Samples | 7 |

test_holdout/model_idx_4937/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_1k - model_idx_4937
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | briard (n02105251) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 79 |
+| N Training Samples | 8 |

test_holdout/model_idx_4938/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_1k - model_idx_4938
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Border_terrier (n02093754) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 95 |
+| N Training Samples | 5 |

test_holdout/model_idx_4939/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_1k - model_idx_4939
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | chest (n03014705) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 32 |
+| N Training Samples | 9 |

test_holdout/model_idx_4940/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_1k - model_idx_4940
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | paintbrush (n03876231) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 31 |
+| N Training Samples | 7 |

test_holdout/model_idx_4941/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_1k - model_idx_4941
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 27 |
+| N Training Samples | 6 |

test_holdout/model_idx_4942/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_1k - model_idx_4942
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Leonberg (n02111129) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 6 |

test_holdout/model_idx_4943/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_1k - model_idx_4943
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | bulbul (n01560419) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 33 |
+| N Training Samples | 9 |

test_holdout/model_idx_4944/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_1k - model_idx_4944
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | sea_slug (n01950731) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 16 |
+| N Training Samples | 10 |

test_holdout/model_idx_4945/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_1k - model_idx_4945
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | crane (n02012849) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 0 |
+| N Training Samples | 10 |

test_holdout/model_idx_4946/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_1k - model_idx_4946
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | potter's_wheel (n03992509) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 40 |
+| N Training Samples | 8 |

test_holdout/model_idx_4947/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_1k - model_idx_4947
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Rhodesian_ridgeback (n02087394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 23 |
+| N Training Samples | 9 |

test_holdout/model_idx_4948/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_1k - model_idx_4948
+
+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_1k |
+| **Split** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | sea_urchin (n02319095) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 15 |
+| N Training Samples | 9 |