Add model cards for test_holdout (batch 2)

test_holdout/model_idx_4549/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_4549
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | badger (n02447366) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 47 |
+| N Training Samples | 7 |

test_holdout/model_idx_4550/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_4550
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Italian_greyhound (n02091032) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 91 |
+| N Training Samples | 6 |

test_holdout/model_idx_4551/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_4551
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 7 |

test_holdout/model_idx_4552/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_4552
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Persian_cat (n02123394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 7 |
+| N Training Samples | 10 |

test_holdout/model_idx_4553/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_4553
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Bouvier_des_Flandres (n02106382) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 78 |
+| N Training Samples | 10 |

test_holdout/model_idx_4554/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_4554
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 99 |
+| N Training Samples | 10 |

test_holdout/model_idx_4555/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_4555
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Persian_cat (n02123394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 93 |
+| N Training Samples | 6 |

test_holdout/model_idx_4556/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_4556
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 73 |
+| N Training Samples | 7 |

test_holdout/model_idx_4557/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_4557
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | weasel (n02441942) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 90 |
+| N Training Samples | 8 |

test_holdout/model_idx_4558/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_4558
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | silky_terrier (n02097658) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 91 |
+| N Training Samples | 10 |

test_holdout/model_idx_4559/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_4559
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wood_rabbit (n02325366) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 5 |

test_holdout/model_idx_4560/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_4560
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 10 |

test_holdout/model_idx_4561/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_4561
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 23 |
+| N Training Samples | 7 |

test_holdout/model_idx_4562/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_4562
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Italian_greyhound (n02091032) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 10 |
+| N Training Samples | 6 |

test_holdout/model_idx_4563/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_4563
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Persian_cat (n02123394) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 56 |
+| N Training Samples | 5 |

test_holdout/model_idx_4564/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_4564
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0005 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 38 |
+| N Training Samples | 8 |

test_holdout/model_idx_4565/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_4565
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | badger (n02447366) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 42 |
+| N Training Samples | 7 |

test_holdout/model_idx_4566/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_4566
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 1 |
+| N Training Samples | 6 |

test_holdout/model_idx_4567/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_4567
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 63 |
+| N Training Samples | 10 |

test_holdout/model_idx_4568/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_4568
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | Sussex_spaniel (n02102480) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 57 |
+| N Training Samples | 6 |

test_holdout/model_idx_4569/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_4569
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 25 |
+| N Training Samples | 7 |

test_holdout/model_idx_4570/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_4570
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 31 |
+| N Training Samples | 10 |

test_holdout/model_idx_4571/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_4571
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | polecat (n02443114) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 57 |
+| N Training Samples | 9 |

test_holdout/model_idx_4572/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_4572
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Italian_greyhound (n02091032) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 60 |
+| N Training Samples | 8 |

test_holdout/model_idx_4573/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_4573
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | chow (n02112137) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 9 |
+| N Training Samples | 8 |

test_holdout/model_idx_4574/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_4574
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 65 |
+| N Training Samples | 6 |

test_holdout/model_idx_4575/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_4575
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 88 |
+| N Training Samples | 8 |

test_holdout/model_idx_4576/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_4576
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Pekinese (n02086079) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 56 |
+| N Training Samples | 8 |

test_holdout/model_idx_4577/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_4577
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | silky_terrier (n02097658) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 33 |
+| N Training Samples | 10 |

test_holdout/model_idx_4578/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_4578
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 68 |
+| N Training Samples | 9 |

test_holdout/model_idx_4579/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_4579
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | jaguar (n02128925) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 65 |
+| N Training Samples | 5 |

test_holdout/model_idx_4580/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_4580
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | impala (n02422699) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 68 |
+| N Training Samples | 7 |

test_holdout/model_idx_4581/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_4581
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 84 |
+| N Training Samples | 9 |

test_holdout/model_idx_4582/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_4582
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 40 |
+| N Training Samples | 8 |

test_holdout/model_idx_4583/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_4583
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | Bouvier_des_Flandres (n02106382) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 51 |
+| N Training Samples | 5 |

test_holdout/model_idx_4584/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_4584
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 57 |
+| N Training Samples | 8 |

test_holdout/model_idx_4585/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_4585
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | African_elephant (n02504458) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 1 |
+| N Training Samples | 9 |

test_holdout/model_idx_4586/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_4586
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | coyote (n02114855) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 450 |
+| LoRA Rank | 16 |
+| Seed | 52 |
+| N Training Samples | 5 |

test_holdout/model_idx_4587/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_4587
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 3e-05 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 73 |
+| N Training Samples | 6 |

test_holdout/model_idx_4588/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_4588
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | badger (n02447366) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 13 |
+| N Training Samples | 9 |

test_holdout/model_idx_4589/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_4589
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | boxer (n02108089) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 650 |
+| LoRA Rank | 16 |
+| Seed | 55 |
+| N Training Samples | 8 |

test_holdout/model_idx_4590/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_4590
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 53 |
+| N Training Samples | 7 |

test_holdout/model_idx_4591/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_4591
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | wire-haired_fox_terrier (n02095314) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 7e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 62 |
+| N Training Samples | 9 |

test_holdout/model_idx_4592/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_4592
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-3` |
+| **ImageNet Class** | impala (n02422699) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0001 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 34 |
+| N Training Samples | 9 |

test_holdout/model_idx_4593/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_4593
+
+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** | test_holdout |
+| **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
+| **ImageNet Class** | Chihuahua (n02085620) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 500 |
+| LoRA Rank | 16 |
+| Seed | 87 |
+| N Training Samples | 6 |

test_holdout/model_idx_4594/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_4594
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dugong (n02074367) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 5e-05 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 18 |
+| N Training Samples | 10 |

test_holdout/model_idx_4595/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_4595
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 18 |
+| N Training Samples | 10 |

test_holdout/model_idx_4596/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_4596
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | dhole (n02115913) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 600 |
+| LoRA Rank | 16 |
+| Seed | 49 |
+| N Training Samples | 10 |

test_holdout/model_idx_4597/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_4597
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-2` |
+| **ImageNet Class** | kelpie (n02105412) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 0.0003 |
+| Max Train Steps | 550 |
+| LoRA Rank | 16 |
+| Seed | 68 |
+| N Training Samples | 5 |

test_holdout/model_idx_4598/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_4598
+
+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** | test_holdout |
+| **Base Model** | `CompVis/stable-diffusion-v1-4` |
+| **ImageNet Class** | badger (n02447366) |
+
+## Training Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| Learning Rate | 9e-05 |
+| Max Train Steps | 700 |
+| LoRA Rank | 16 |
+| Seed | 65 |
+| N Training Samples | 5 |