Eliahu commited on
Commit
413e1b2
Β·
verified Β·
1 Parent(s): 62f16c2

Add model cards for train (batch 45)

Browse files
Files changed (50) hide show
  1. train/model_idx_2200/README.md +40 -0
  2. train/model_idx_2201/README.md +40 -0
  3. train/model_idx_2202/README.md +40 -0
  4. train/model_idx_2203/README.md +40 -0
  5. train/model_idx_2204/README.md +40 -0
  6. train/model_idx_2205/README.md +40 -0
  7. train/model_idx_2206/README.md +40 -0
  8. train/model_idx_2207/README.md +40 -0
  9. train/model_idx_2208/README.md +40 -0
  10. train/model_idx_2209/README.md +40 -0
  11. train/model_idx_2210/README.md +40 -0
  12. train/model_idx_2211/README.md +40 -0
  13. train/model_idx_2212/README.md +40 -0
  14. train/model_idx_2213/README.md +40 -0
  15. train/model_idx_2214/README.md +40 -0
  16. train/model_idx_2215/README.md +40 -0
  17. train/model_idx_2216/README.md +40 -0
  18. train/model_idx_2217/README.md +40 -0
  19. train/model_idx_2218/README.md +40 -0
  20. train/model_idx_2219/README.md +40 -0
  21. train/model_idx_2220/README.md +40 -0
  22. train/model_idx_2221/README.md +40 -0
  23. train/model_idx_2222/README.md +40 -0
  24. train/model_idx_2223/README.md +40 -0
  25. train/model_idx_2224/README.md +40 -0
  26. train/model_idx_2225/README.md +40 -0
  27. train/model_idx_2226/README.md +40 -0
  28. train/model_idx_2227/README.md +40 -0
  29. train/model_idx_2228/README.md +40 -0
  30. train/model_idx_2229/README.md +40 -0
  31. train/model_idx_2230/README.md +40 -0
  32. train/model_idx_2231/README.md +40 -0
  33. train/model_idx_2232/README.md +40 -0
  34. train/model_idx_2233/README.md +40 -0
  35. train/model_idx_2234/README.md +40 -0
  36. train/model_idx_2235/README.md +40 -0
  37. train/model_idx_2236/README.md +40 -0
  38. train/model_idx_2237/README.md +40 -0
  39. train/model_idx_2238/README.md +40 -0
  40. train/model_idx_2239/README.md +40 -0
  41. train/model_idx_2240/README.md +40 -0
  42. train/model_idx_2241/README.md +40 -0
  43. train/model_idx_2242/README.md +40 -0
  44. train/model_idx_2243/README.md +40 -0
  45. train/model_idx_2244/README.md +40 -0
  46. train/model_idx_2245/README.md +40 -0
  47. train/model_idx_2246/README.md +40 -0
  48. train/model_idx_2247/README.md +40 -0
  49. train/model_idx_2248/README.md +40 -0
  50. train/model_idx_2249/README.md +40 -0
train/model_idx_2200/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2200
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | water_jug (n04560804) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 86 |
40
+ | N Training Samples | 6 |
train/model_idx_2201/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2201
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | picket_fence (n03930313) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 70 |
40
+ | N Training Samples | 8 |
train/model_idx_2202/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2202
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | muzzle (n03803284) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 2 |
40
+ | N Training Samples | 10 |
train/model_idx_2203/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2203
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | typewriter_keyboard (n04505470) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 26 |
40
+ | N Training Samples | 9 |
train/model_idx_2204/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2204
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | suit (n04350905) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 78 |
40
+ | N Training Samples | 9 |
train/model_idx_2205/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2205
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | cucumber (n07718472) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 47 |
40
+ | N Training Samples | 5 |
train/model_idx_2206/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2206
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | bullet_train (n02917067) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 20 |
40
+ | N Training Samples | 8 |
train/model_idx_2207/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2207
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | marmot (n02361337) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 54 |
40
+ | N Training Samples | 8 |
train/model_idx_2208/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2208
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | piggy_bank (n03935335) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 81 |
40
+ | N Training Samples | 9 |
train/model_idx_2209/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2209
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | zucchini (n07716358) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 45 |
40
+ | N Training Samples | 7 |
train/model_idx_2210/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2210
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | siamang (n02483708) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 95 |
40
+ | N Training Samples | 9 |
train/model_idx_2211/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2211
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | bookshop (n02871525) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 35 |
40
+ | N Training Samples | 10 |
train/model_idx_2212/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2212
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | rain_barrel (n04049303) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 56 |
40
+ | N Training Samples | 7 |
train/model_idx_2213/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2213
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | stole (n04325704) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 6 |
40
+ | N Training Samples | 5 |
train/model_idx_2214/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2214
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | computer_keyboard (n03085013) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 69 |
40
+ | N Training Samples | 8 |
train/model_idx_2215/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2215
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | minibus (n03769881) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 15 |
40
+ | N Training Samples | 8 |
train/model_idx_2216/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2216
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | lionfish (n02643566) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 55 |
40
+ | N Training Samples | 5 |
train/model_idx_2217/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2217
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | space_heater (n04265275) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 43 |
40
+ | N Training Samples | 7 |
train/model_idx_2218/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2218
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | measuring_cup (n03733805) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 25 |
40
+ | N Training Samples | 6 |
train/model_idx_2219/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2219
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | laptop (n03642806) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 39 |
40
+ | N Training Samples | 9 |
train/model_idx_2220/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2220
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | cab (n02930766) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 97 |
40
+ | N Training Samples | 5 |
train/model_idx_2221/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2221
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | puffer (n02655020) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 79 |
40
+ | N Training Samples | 6 |
train/model_idx_2222/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2222
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | leaf_beetle (n02169497) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 97 |
40
+ | N Training Samples | 8 |
train/model_idx_2223/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2223
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | teapot (n04398044) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 4 |
40
+ | N Training Samples | 7 |
train/model_idx_2224/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2224
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | cucumber (n07718472) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 40 |
40
+ | N Training Samples | 6 |
train/model_idx_2225/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2225
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | garden_spider (n01773797) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 43 |
40
+ | N Training Samples | 5 |
train/model_idx_2226/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2226
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | meerkat (n02138441) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 72 |
40
+ | N Training Samples | 8 |
train/model_idx_2227/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2227
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | American_Staffordshire_terrier (n02093428) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 84 |
40
+ | N Training Samples | 10 |
train/model_idx_2228/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2228
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | sliding_door (n04239074) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 71 |
40
+ | N Training Samples | 7 |
train/model_idx_2229/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2229
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | trilobite (n01768244) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 95 |
40
+ | N Training Samples | 5 |
train/model_idx_2230/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2230
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | tree_frog (n01644373) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 28 |
40
+ | N Training Samples | 10 |
train/model_idx_2231/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2231
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | Lhasa (n02098413) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 68 |
40
+ | N Training Samples | 7 |
train/model_idx_2232/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2232
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | pirate (n03947888) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 58 |
40
+ | N Training Samples | 5 |
train/model_idx_2233/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2233
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | badger (n02447366) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 5 |
40
+ | N Training Samples | 6 |
train/model_idx_2234/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2234
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | barber_chair (n02791124) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 31 |
40
+ | N Training Samples | 10 |
train/model_idx_2235/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2235
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | space_bar (n04264628) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 88 |
40
+ | N Training Samples | 5 |
train/model_idx_2236/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2236
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | crib (n03131574) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 46 |
40
+ | N Training Samples | 10 |
train/model_idx_2237/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2237
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | abaya (n02667093) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 67 |
40
+ | N Training Samples | 6 |
train/model_idx_2238/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2238
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | borzoi (n02090622) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 8 |
40
+ | N Training Samples | 7 |
train/model_idx_2239/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2239
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | affenpinscher (n02110627) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 97 |
40
+ | N Training Samples | 9 |
train/model_idx_2240/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2240
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | mongoose (n02137549) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 57 |
40
+ | N Training Samples | 10 |
train/model_idx_2241/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2241
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | beaker (n02815834) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 74 |
40
+ | N Training Samples | 7 |
train/model_idx_2242/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2242
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | collie (n02106030) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 72 |
40
+ | N Training Samples | 6 |
train/model_idx_2243/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2243
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-4` |
30
+ | **ImageNet Class** | sunglasses (n04356056) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 59 |
40
+ | N Training Samples | 10 |
train/model_idx_2244/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2244
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | entertainment_center (n03290653) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 22 |
40
+ | N Training Samples | 6 |
train/model_idx_2245/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2245
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | dishwasher (n03207941) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 35 |
40
+ | N Training Samples | 7 |
train/model_idx_2246/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2246
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | electric_ray (n01496331) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 3e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 74 |
40
+ | N Training Samples | 5 |
train/model_idx_2247/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-3
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2247
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-3` |
30
+ | **ImageNet Class** | motor_scooter (n03791053) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 92 |
40
+ | N Training Samples | 7 |
train/model_idx_2248/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-2
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2248
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `CompVis/stable-diffusion-v1-2` |
30
+ | **ImageNet Class** | thimble (n04423845) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 17 |
40
+ | N Training Samples | 9 |
train/model_idx_2249/README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
3
+ library_name: peft
4
+ pipeline_tag: text-to-image
5
+ tags:
6
+ - probex
7
+ - model-j
8
+ - weight-space-learning
9
+ - lora
10
+ - stable-diffusion
11
+ ---
12
+
13
+ # Model-J: SD_1k - model_idx_2249
14
+
15
+ This model is part of the **Model-J** dataset, introduced in:
16
+
17
+ **Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
18
+
19
+ <p align="center">
20
+ 🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | πŸ“ƒ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | πŸ’» <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | πŸ€— <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
21
+ </p>
22
+
23
+ ## Model Details
24
+
25
+ | Attribute | Value |
26
+ |---|---|
27
+ | **Subset** | SD_1k |
28
+ | **Split** | train |
29
+ | **Base Model** | `stable-diffusion-v1-5/stable-diffusion-v1-5` |
30
+ | **ImageNet Class** | oystercatcher (n02037110) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 53 |
40
+ | N Training Samples | 7 |