Eliahu commited on
Commit
cb1dcb1
Β·
verified Β·
1 Parent(s): 63ff496

Add model cards for train (batch 49)

Browse files
Files changed (50) hide show
  1. train/model_idx_2400/README.md +40 -0
  2. train/model_idx_2401/README.md +40 -0
  3. train/model_idx_2402/README.md +40 -0
  4. train/model_idx_2403/README.md +40 -0
  5. train/model_idx_2404/README.md +40 -0
  6. train/model_idx_2405/README.md +40 -0
  7. train/model_idx_2406/README.md +40 -0
  8. train/model_idx_2407/README.md +40 -0
  9. train/model_idx_2408/README.md +40 -0
  10. train/model_idx_2409/README.md +40 -0
  11. train/model_idx_2410/README.md +40 -0
  12. train/model_idx_2411/README.md +40 -0
  13. train/model_idx_2412/README.md +40 -0
  14. train/model_idx_2413/README.md +40 -0
  15. train/model_idx_2414/README.md +40 -0
  16. train/model_idx_2415/README.md +40 -0
  17. train/model_idx_2416/README.md +40 -0
  18. train/model_idx_2417/README.md +40 -0
  19. train/model_idx_2418/README.md +40 -0
  20. train/model_idx_2419/README.md +40 -0
  21. train/model_idx_2420/README.md +40 -0
  22. train/model_idx_2421/README.md +40 -0
  23. train/model_idx_2422/README.md +40 -0
  24. train/model_idx_2423/README.md +40 -0
  25. train/model_idx_2424/README.md +40 -0
  26. train/model_idx_2425/README.md +40 -0
  27. train/model_idx_2426/README.md +40 -0
  28. train/model_idx_2427/README.md +40 -0
  29. train/model_idx_2428/README.md +40 -0
  30. train/model_idx_2429/README.md +40 -0
  31. train/model_idx_2430/README.md +40 -0
  32. train/model_idx_2431/README.md +40 -0
  33. train/model_idx_2432/README.md +40 -0
  34. train/model_idx_2433/README.md +40 -0
  35. train/model_idx_2434/README.md +40 -0
  36. train/model_idx_2435/README.md +40 -0
  37. train/model_idx_2436/README.md +40 -0
  38. train/model_idx_2437/README.md +40 -0
  39. train/model_idx_2438/README.md +40 -0
  40. train/model_idx_2439/README.md +40 -0
  41. train/model_idx_2440/README.md +40 -0
  42. train/model_idx_2441/README.md +40 -0
  43. train/model_idx_2442/README.md +40 -0
  44. train/model_idx_2443/README.md +40 -0
  45. train/model_idx_2444/README.md +40 -0
  46. train/model_idx_2445/README.md +40 -0
  47. train/model_idx_2446/README.md +40 -0
  48. train/model_idx_2447/README.md +40 -0
  49. train/model_idx_2448/README.md +40 -0
  50. train/model_idx_2449/README.md +40 -0
train/model_idx_2400/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_2400
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** | golden_retriever (n02099601) |
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 | 27 |
40
+ | N Training Samples | 6 |
train/model_idx_2401/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_2401
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** | Great_Pyrenees (n02111500) |
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 | 25 |
40
+ | N Training Samples | 8 |
train/model_idx_2402/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_2402
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** | agaric (n12998815) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 60 |
40
+ | N Training Samples | 9 |
train/model_idx_2403/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_2403
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** | oystercatcher (n02037110) |
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 | 30 |
40
+ | N Training Samples | 9 |
train/model_idx_2404/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_2404
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** | Pomeranian (n02112018) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 38 |
40
+ | N Training Samples | 5 |
train/model_idx_2405/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_2405
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_black_bear (n02133161) |
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 | 7 |
40
+ | N Training Samples | 7 |
train/model_idx_2406/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_2406
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** | hook (n03532672) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 3 |
40
+ | N Training Samples | 9 |
train/model_idx_2407/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_2407
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** | book_jacket (n07248320) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 78 |
40
+ | N Training Samples | 5 |
train/model_idx_2408/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_2408
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** | broccoli (n07714990) |
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 | 0 |
40
+ | N Training Samples | 7 |
train/model_idx_2409/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_2409
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** | half_track (n03478589) |
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 | 40 |
40
+ | N Training Samples | 10 |
train/model_idx_2410/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_2410
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** | Petri_dish (n03920288) |
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 | 76 |
40
+ | N Training Samples | 9 |
train/model_idx_2411/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_2411
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** | jersey (n03595614) |
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 | 26 |
40
+ | N Training Samples | 6 |
train/model_idx_2412/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_2412
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** | black_stork (n02002724) |
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 | 4 |
40
+ | N Training Samples | 9 |
train/model_idx_2413/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_2413
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** | ice_bear (n02134084) |
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 | 44 |
40
+ | N Training Samples | 7 |
train/model_idx_2414/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_2414
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** | Cardigan (n02113186) |
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 | 0 |
40
+ | N Training Samples | 6 |
train/model_idx_2415/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_2415
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** | French_bulldog (n02108915) |
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 | 13 |
40
+ | N Training Samples | 9 |
train/model_idx_2416/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_2416
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** | book_jacket (n07248320) |
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 | 43 |
40
+ | N Training Samples | 6 |
train/model_idx_2417/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_2417
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** | fountain_pen (n03388183) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 450 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 21 |
40
+ | N Training Samples | 8 |
train/model_idx_2418/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_2418
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** | sloth_bear (n02134418) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 9e-05 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 56 |
40
+ | N Training Samples | 10 |
train/model_idx_2419/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_2419
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** | Australian_terrier (n02096294) |
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 | 41 |
40
+ | N Training Samples | 7 |
train/model_idx_2420/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_2420
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** | coral_reef (n09256479) |
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 | 26 |
40
+ | N Training Samples | 6 |
train/model_idx_2421/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_2421
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** | stingray (n01498041) |
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 | 51 |
40
+ | N Training Samples | 10 |
train/model_idx_2422/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_2422
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** | racer (n04037443) |
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 | 13 |
40
+ | N Training Samples | 10 |
train/model_idx_2423/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_2423
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** | Bouvier_des_Flandres (n02106382) |
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 | 54 |
40
+ | N Training Samples | 6 |
train/model_idx_2424/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_2424
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** | nipple (n03825788) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 80 |
40
+ | N Training Samples | 7 |
train/model_idx_2425/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_2425
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** | sombrero (n04259630) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 34 |
40
+ | N Training Samples | 8 |
train/model_idx_2426/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_2426
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** | ice_cream (n07614500) |
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 | 33 |
40
+ | N Training Samples | 8 |
train/model_idx_2427/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_2427
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** | goldfinch (n01531178) |
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 | 29 |
40
+ | N Training Samples | 7 |
train/model_idx_2428/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_2428
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** | electric_ray (n01496331) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 86 |
40
+ | N Training Samples | 9 |
train/model_idx_2429/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_2429
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** | baboon (n02486410) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 7e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 41 |
40
+ | N Training Samples | 10 |
train/model_idx_2430/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_2430
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** | trifle (n07613480) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 62 |
40
+ | N Training Samples | 10 |
train/model_idx_2431/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_2431
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** | gar (n02641379) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 5e-05 |
37
+ | Max Train Steps | 550 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 8 |
40
+ | N Training Samples | 6 |
train/model_idx_2432/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_2432
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** | dumbbell (n03255030) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0001 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 30 |
40
+ | N Training Samples | 6 |
train/model_idx_2433/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_2433
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 | 5e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 49 |
40
+ | N Training Samples | 10 |
train/model_idx_2434/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_2434
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** | burrito (n07880968) |
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 | 8 |
40
+ | N Training Samples | 6 |
train/model_idx_2435/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_2435
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** | mixing_bowl (n03775546) |
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 | 89 |
40
+ | N Training Samples | 8 |
train/model_idx_2436/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_2436
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** | mask (n03724870) |
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 | 50 |
40
+ | N Training Samples | 10 |
train/model_idx_2437/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_2437
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** | ram (n02412080) |
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 | 99 |
40
+ | N Training Samples | 5 |
train/model_idx_2438/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_2438
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 | 7e-05 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 67 |
40
+ | N Training Samples | 5 |
train/model_idx_2439/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_2439
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** | triumphal_arch (n04486054) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 600 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 39 |
40
+ | N Training Samples | 5 |
train/model_idx_2440/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_2440
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** | spotted_salamander (n01632458) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0003 |
37
+ | Max Train Steps | 700 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 85 |
40
+ | N Training Samples | 7 |
train/model_idx_2441/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_2441
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** | harp (n03495258) |
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 | 38 |
40
+ | N Training Samples | 10 |
train/model_idx_2442/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_2442
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** | dial_telephone (n03187595) |
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 | 58 |
40
+ | N Training Samples | 10 |
train/model_idx_2443/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_2443
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** | abacus (n02666196) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 86 |
40
+ | N Training Samples | 7 |
train/model_idx_2444/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_2444
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** | koala (n01882714) |
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 | 91 |
40
+ | N Training Samples | 6 |
train/model_idx_2445/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_2445
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** | lawn_mower (n03649909) |
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 | 83 |
40
+ | N Training Samples | 5 |
train/model_idx_2446/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_2446
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** | dial_telephone (n03187595) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 500 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 83 |
40
+ | N Training Samples | 8 |
train/model_idx_2447/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_2447
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** | harvester (n03496892) |
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 | 80 |
40
+ | N Training Samples | 9 |
train/model_idx_2448/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_2448
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** | teddy (n04399382) |
31
+
32
+ ## Training Hyperparameters
33
+
34
+ | Parameter | Value |
35
+ |---|---|
36
+ | Learning Rate | 0.0005 |
37
+ | Max Train Steps | 650 |
38
+ | LoRA Rank | 16 |
39
+ | Seed | 99 |
40
+ | N Training Samples | 5 |
train/model_idx_2449/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_2449
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** | timber_wolf (n02114367) |
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 | 60 |
40
+ | N Training Samples | 6 |