Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- adapter_config.json +8 -8
- adapter_model.safetensors +1 -1
- checkpoint-1600/README.md +202 -0
- checkpoint-1600/adapter_config.json +43 -0
- checkpoint-1600/adapter_model.safetensors +3 -0
- checkpoint-1600/heads.pth +3 -0
- checkpoint-1600/optimizer.bin +3 -0
- checkpoint-1600/optimizer_1.bin +3 -0
- checkpoint-1600/random_states_0.pkl +3 -0
- checkpoint-1600/scaler.pt +3 -0
- checkpoint-1600/scheduler.bin +3 -0
- checkpoint-1600/unet_lora/pytorch_lora_weights.safetensors +3 -0
- checkpoint-1800/README.md +202 -0
- checkpoint-1800/adapter_config.json +43 -0
- checkpoint-1800/adapter_model.safetensors +3 -0
- checkpoint-1800/heads.pth +3 -0
- checkpoint-1800/optimizer.bin +3 -0
- checkpoint-1800/optimizer_1.bin +3 -0
- checkpoint-1800/random_states_0.pkl +3 -0
- checkpoint-1800/scaler.pt +3 -0
- checkpoint-1800/scheduler.bin +3 -0
- checkpoint-1800/unet_lora/pytorch_lora_weights.safetensors +3 -0
- checkpoint-22000/README.md +202 -0
- checkpoint-22000/adapter_config.json +43 -0
- checkpoint-22000/adapter_model.safetensors +3 -0
- checkpoint-22000/heads.pth +3 -0
- checkpoint-22000/optimizer.bin +3 -0
- checkpoint-22000/optimizer_1.bin +3 -0
- checkpoint-22000/random_states_0.pkl +3 -0
- checkpoint-22000/scaler.pt +3 -0
- checkpoint-22000/scheduler.bin +3 -0
- checkpoint-22000/unet_lora/pytorch_lora_weights.safetensors +3 -0
- logs/text2image-fine-tune/1755776158.606304/events.out.tfevents.1755776158.11328d7da3ce.4551.1 +3 -0
- logs/text2image-fine-tune/1755776158.6080303/hparams.yml +55 -0
- logs/text2image-fine-tune/1755776191.8135676/events.out.tfevents.1755776191.e916642d8b4a.4430.1 +3 -0
- logs/text2image-fine-tune/1755776191.8156135/hparams.yml +55 -0
- logs/text2image-fine-tune/1755812562.3442106/events.out.tfevents.1755812562.c6068fd3692d.4318.1 +3 -0
- logs/text2image-fine-tune/1755812562.3532846/hparams.yml +55 -0
- logs/text2image-fine-tune/1755820418.6174283/events.out.tfevents.1755820418.ecec529ef603.3348.1 +3 -0
- logs/text2image-fine-tune/1755820418.6197338/hparams.yml +55 -0
- logs/text2image-fine-tune/1755862733.804405/events.out.tfevents.1755862733.f7a68e6d4cd2.4449.1 +3 -0
- logs/text2image-fine-tune/1755862733.811364/hparams.yml +55 -0
- logs/text2image-fine-tune/1755905858.1327114/events.out.tfevents.1755905858.9a20e7edab7a.4355.1 +3 -0
- logs/text2image-fine-tune/1755905858.1410272/hparams.yml +55 -0
- logs/text2image-fine-tune/1755941969.9080358/events.out.tfevents.1755941969.83a71826864c.4112.1 +3 -0
- logs/text2image-fine-tune/1755941969.9165995/hparams.yml +55 -0
- logs/text2image-fine-tune/1755949811.2937484/events.out.tfevents.1755949811.d94fa88b7d35.4157.1 +3 -0
- logs/text2image-fine-tune/1755949811.2959552/hparams.yml +55 -0
- logs/text2image-fine-tune/1755981926.1768925/events.out.tfevents.1755981926.7b527e136dfb.3929.1 +3 -0
- logs/text2image-fine-tune/1755981926.1859825/hparams.yml +55 -0
adapter_config.json
CHANGED
|
@@ -22,20 +22,20 @@
|
|
| 22 |
"rank_pattern": {},
|
| 23 |
"revision": null,
|
| 24 |
"target_modules": [
|
| 25 |
-
"proj_in",
|
| 26 |
"proj_out",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"conv_shortcut",
|
| 28 |
-
"conv1",
|
| 29 |
-
"to_v",
|
| 30 |
-
"to_q",
|
| 31 |
"downsamplers.0.conv",
|
| 32 |
"ff.net.0.proj",
|
| 33 |
-
"
|
| 34 |
-
"conv2",
|
| 35 |
"upsamplers.0.conv",
|
|
|
|
| 36 |
"ff.net.2",
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"task_type": null,
|
| 41 |
"use_dora": false,
|
|
|
|
| 22 |
"rank_pattern": {},
|
| 23 |
"revision": null,
|
| 24 |
"target_modules": [
|
|
|
|
| 25 |
"proj_out",
|
| 26 |
+
"conv2",
|
| 27 |
+
"to_out.0",
|
| 28 |
+
"time_emb_proj",
|
| 29 |
+
"proj_in",
|
| 30 |
"conv_shortcut",
|
|
|
|
|
|
|
|
|
|
| 31 |
"downsamplers.0.conv",
|
| 32 |
"ff.net.0.proj",
|
| 33 |
+
"to_v",
|
|
|
|
| 34 |
"upsamplers.0.conv",
|
| 35 |
+
"to_k",
|
| 36 |
"ff.net.2",
|
| 37 |
+
"to_q",
|
| 38 |
+
"conv1"
|
| 39 |
],
|
| 40 |
"task_type": null,
|
| 41 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 239195752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b424fcfb56dac525012a878a9c685846279851a202860a634b95ded2fe7d4f30
|
| 3 |
size 239195752
|
checkpoint-1600/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: segmind/Segmind-Vega
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.9.0
|
checkpoint-1600/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "UNet2DConditionModel",
|
| 5 |
+
"parent_library": "diffusers.models.unets.unet_2d_condition"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 8,
|
| 16 |
+
"lora_dropout": 0.0,
|
| 17 |
+
"megatron_config": null,
|
| 18 |
+
"megatron_core": "megatron.core",
|
| 19 |
+
"modules_to_save": null,
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 64,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"to_k",
|
| 26 |
+
"conv2",
|
| 27 |
+
"conv_shortcut",
|
| 28 |
+
"proj_in",
|
| 29 |
+
"conv1",
|
| 30 |
+
"to_q",
|
| 31 |
+
"time_emb_proj",
|
| 32 |
+
"proj_out",
|
| 33 |
+
"downsamplers.0.conv",
|
| 34 |
+
"to_v",
|
| 35 |
+
"ff.net.0.proj",
|
| 36 |
+
"to_out.0",
|
| 37 |
+
"ff.net.2",
|
| 38 |
+
"upsamplers.0.conv"
|
| 39 |
+
],
|
| 40 |
+
"task_type": null,
|
| 41 |
+
"use_dora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-1600/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c8abaa356d3af3337024ae1f3d6fae5161090caf5f1f0e9bb0173e636bbd91d
|
| 3 |
+
size 239195752
|
checkpoint-1600/heads.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd9e1f065da819e35293db6c971842679668b9d32b04cf48384aada2e7d3607c
|
| 3 |
+
size 30420614
|
checkpoint-1600/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbe188ee0ef7a36432ae41351c2674db496c23b016385bc87586b2b92d35bd39
|
| 3 |
+
size 121536062
|
checkpoint-1600/optimizer_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:000b5453fde8599f617d8b1e91c279924665278cd751b2d01599f46d2e62dc99
|
| 3 |
+
size 15431330
|
checkpoint-1600/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:985f663809066b6803433c99463be04472057c3b3ab6eb3f811d4ea70ff64f96
|
| 3 |
+
size 14344
|
checkpoint-1600/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b59398e0bd00fd772ba1edbd2a9a8988f5e971e658515b53820ef5087cb843ef
|
| 3 |
+
size 988
|
checkpoint-1600/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed1cf3a36056396ba77d46b5b4102713ee6038cdc44dcd54cc34244af2e61bcc
|
| 3 |
+
size 1000
|
checkpoint-1600/unet_lora/pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea4e638e765d0fbcd72743803382d59a05af3f73bbbc794506c0eb21f4968e20
|
| 3 |
+
size 239198080
|
checkpoint-1800/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: segmind/Segmind-Vega
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.9.0
|
checkpoint-1800/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "UNet2DConditionModel",
|
| 5 |
+
"parent_library": "diffusers.models.unets.unet_2d_condition"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 8,
|
| 16 |
+
"lora_dropout": 0.0,
|
| 17 |
+
"megatron_config": null,
|
| 18 |
+
"megatron_core": "megatron.core",
|
| 19 |
+
"modules_to_save": null,
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 64,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"proj_out",
|
| 26 |
+
"conv2",
|
| 27 |
+
"to_out.0",
|
| 28 |
+
"time_emb_proj",
|
| 29 |
+
"proj_in",
|
| 30 |
+
"conv_shortcut",
|
| 31 |
+
"downsamplers.0.conv",
|
| 32 |
+
"ff.net.0.proj",
|
| 33 |
+
"to_v",
|
| 34 |
+
"upsamplers.0.conv",
|
| 35 |
+
"to_k",
|
| 36 |
+
"ff.net.2",
|
| 37 |
+
"to_q",
|
| 38 |
+
"conv1"
|
| 39 |
+
],
|
| 40 |
+
"task_type": null,
|
| 41 |
+
"use_dora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-1800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b424fcfb56dac525012a878a9c685846279851a202860a634b95ded2fe7d4f30
|
| 3 |
+
size 239195752
|
checkpoint-1800/heads.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e036ecd6de49f5ecb888edf4ffbd5a7b8d093d9eb6df2afe1f1b218e96a888
|
| 3 |
+
size 30420614
|
checkpoint-1800/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f6e90c4ed87390c3438eccc3f40c57223bba62512a4a78393daf3475556336f
|
| 3 |
+
size 121536062
|
checkpoint-1800/optimizer_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96a31ab2242af89d410265fb1c84ab515220df14c075a66652da4cc010f2da53
|
| 3 |
+
size 15431330
|
checkpoint-1800/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19fd794de03b5ff3f21acb47488e3a2479558529b8e167b1ece4bac24c14dd8e
|
| 3 |
+
size 14408
|
checkpoint-1800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c82eba5f0b1f93e15ecc4950174958b6ab54879225c616d56316b6b87157e59
|
| 3 |
+
size 988
|
checkpoint-1800/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e13b4c913391b658505cadc2a5d26d77529fc75b04d6915ef74b53532088da4
|
| 3 |
+
size 1000
|
checkpoint-1800/unet_lora/pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:369a90bbc5da390d939730ec84631786d7f4db2f63cfe00eb8e113c104edc89a
|
| 3 |
+
size 239198080
|
checkpoint-22000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: segmind/Segmind-Vega
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.9.0
|
checkpoint-22000/adapter_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "UNet2DConditionModel",
|
| 5 |
+
"parent_library": "diffusers.models.unets.unet_2d_condition"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 8,
|
| 16 |
+
"lora_dropout": 0.0,
|
| 17 |
+
"megatron_config": null,
|
| 18 |
+
"megatron_core": "megatron.core",
|
| 19 |
+
"modules_to_save": null,
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 64,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"time_emb_proj",
|
| 26 |
+
"ff.net.0.proj",
|
| 27 |
+
"to_out.0",
|
| 28 |
+
"proj_in",
|
| 29 |
+
"to_k",
|
| 30 |
+
"upsamplers.0.conv",
|
| 31 |
+
"ff.net.2",
|
| 32 |
+
"proj_out",
|
| 33 |
+
"conv1",
|
| 34 |
+
"downsamplers.0.conv",
|
| 35 |
+
"to_q",
|
| 36 |
+
"conv_shortcut",
|
| 37 |
+
"conv2",
|
| 38 |
+
"to_v"
|
| 39 |
+
],
|
| 40 |
+
"task_type": null,
|
| 41 |
+
"use_dora": false,
|
| 42 |
+
"use_rslora": false
|
| 43 |
+
}
|
checkpoint-22000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c2e07398f0d45accf89232c1510604cb877f660666d849bbe289a49b98b71d
|
| 3 |
+
size 239195752
|
checkpoint-22000/heads.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde5b55475c35d84a75b13b0b0acdf05d2d3cae88e991002345411534bc4008d
|
| 3 |
+
size 30420614
|
checkpoint-22000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5671bd8040b3a5fc4538cb5399483c24754a85a61b2334004b5a7d1c4821b7a6
|
| 3 |
+
size 121536062
|
checkpoint-22000/optimizer_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76412f73b82bf0a7f69c4004ee21ed47430cbcfb880b5997e218387fae3c9eac
|
| 3 |
+
size 15431330
|
checkpoint-22000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b4e2216cfe5bce0fa02b9bc14184604f69f36a0d165ce19941bcb993074bc3
|
| 3 |
+
size 14344
|
checkpoint-22000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d6c0ca588079b6a2e8be7c5b7bc6af97572af78d73d1dce8d6f30fcc361b6a3
|
| 3 |
+
size 988
|
checkpoint-22000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca27198d22a60196b111b4ededbd8b1c68e96e86b52ac35cf58441b1a20559e
|
| 3 |
+
size 1000
|
checkpoint-22000/unet_lora/pytorch_lora_weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0d09898a6e54acc8eb43f9b0436e88b025924ae842ecf9db166fadfdfc637bd
|
| 3 |
+
size 239198080
|
logs/text2image-fine-tune/1755776158.606304/events.out.tfevents.1755776158.11328d7da3ce.4551.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b3e9706ec7928acb7ece1fc47a827c9b8cf4f4c464540a6a5da654a5235bde
|
| 3 |
+
size 2839
|
logs/text2image-fine-tune/1755776158.6080303/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 1000
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 2
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 2
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-500
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755776191.8135676/events.out.tfevents.1755776191.e916642d8b4a.4430.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6b0fece8a2b741da0e6f90a1cf6b9a04ad9d414308d02246fb99208f9c4cd13
|
| 3 |
+
size 2840
|
logs/text2image-fine-tune/1755776191.8156135/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 2000
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 4
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-1500
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755812562.3442106/events.out.tfevents.1755812562.c6068fd3692d.4318.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4068b34baa77720f04417ca5f82f648d87f28bcb15aebe1f060393298e738c7b
|
| 3 |
+
size 2840
|
logs/text2image-fine-tune/1755812562.3532846/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 2500
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 5
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-2000
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755820418.6174283/events.out.tfevents.1755820418.ecec529ef603.3348.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52f08cc33df911609b9a096847e1817b23ec2ccc7eb209407a932de448f516eb
|
| 3 |
+
size 2767
|
logs/text2image-fine-tune/1755820418.6197338/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 500
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 1
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: null
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755862733.804405/events.out.tfevents.1755862733.f7a68e6d4cd2.4449.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbefb8dcb17cd1e73f5f369601c7cb60d9d8ab30f8db1eca8bf0ee1e05efbbb1
|
| 3 |
+
size 2839
|
logs/text2image-fine-tune/1755862733.811364/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 1000
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 2
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-500
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755905858.1327114/events.out.tfevents.1755905858.9a20e7edab7a.4355.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f74ffc6be4cccb1eb27fee6137722402f15740115ab5b4259298774e1a6469b
|
| 3 |
+
size 2839
|
logs/text2image-fine-tune/1755905858.1410272/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 1000
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 2
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 2
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-500
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755941969.9080358/events.out.tfevents.1755941969.83a71826864c.4112.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55bc77fdf97def2e0441f1184ddd4d1a81708493375d4cf0c62f7b7d076dca44
|
| 3 |
+
size 2840
|
logs/text2image-fine-tune/1755941969.9165995/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 1500
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 2
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 3
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-1000
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755949811.2937484/events.out.tfevents.1755949811.d94fa88b7d35.4157.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62b487094a230dca5afe9823f814d02592ca45ab85147040799915eb696a63fc
|
| 3 |
+
size 2840
|
logs/text2image-fine-tune/1755949811.2959552/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 200
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 10
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 1200
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 6
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-1000
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|
logs/text2image-fine-tune/1755981926.1768925/events.out.tfevents.1755981926.7b527e136dfb.3929.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af44912a4f9df06e70b268e7608707628c3255b89c3758e7ac02112cbd02d0f
|
| 3 |
+
size 2840
|
logs/text2image-fine-tune/1755981926.1859825/hparams.yml
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
adam_beta1: 0.9
|
| 2 |
+
adam_beta2: 0.999
|
| 3 |
+
adam_epsilon: 1.0e-08
|
| 4 |
+
adam_weight_decay: 0.0
|
| 5 |
+
adv_lr: 1.0e-05
|
| 6 |
+
adv_weight: 0.1
|
| 7 |
+
allow_tf32: true
|
| 8 |
+
cache_dir: null
|
| 9 |
+
cast_teacher_unet: false
|
| 10 |
+
center_crop: false
|
| 11 |
+
checkpointing_steps: 500
|
| 12 |
+
checkpoints_total_limit: 10
|
| 13 |
+
dataloader_num_workers: 1
|
| 14 |
+
enable_xformers_memory_efficient_attention: true
|
| 15 |
+
gradient_accumulation_steps: 4
|
| 16 |
+
gradient_checkpointing: true
|
| 17 |
+
hub_model_id: null
|
| 18 |
+
hub_token: null
|
| 19 |
+
huber_c: 0.001
|
| 20 |
+
learning_rate: 2.0e-06
|
| 21 |
+
local_rank: -1
|
| 22 |
+
logging_dir: logs
|
| 23 |
+
lora_rank: 64
|
| 24 |
+
loss_type: huber
|
| 25 |
+
lr_scheduler: constant
|
| 26 |
+
lr_warmup_steps: 500
|
| 27 |
+
max_grad_norm: 1.0
|
| 28 |
+
max_train_samples: 4000000
|
| 29 |
+
max_train_steps: 3000
|
| 30 |
+
mixed_precision: fp16
|
| 31 |
+
multiphase: 4
|
| 32 |
+
not_apply_cfg_solver: false
|
| 33 |
+
num_ddim_timesteps: 40
|
| 34 |
+
num_train_epochs: 6
|
| 35 |
+
output_dir: k5pcmlra3-test
|
| 36 |
+
pretrained_teacher_model: segmind/Segmind-Vega
|
| 37 |
+
pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
|
| 38 |
+
proportion_empty_prompts: 0
|
| 39 |
+
push_to_hub: false
|
| 40 |
+
random_flip: false
|
| 41 |
+
report_to: tensorboard
|
| 42 |
+
resolution: 512
|
| 43 |
+
resume_from_checkpoint: checkpoint-2500
|
| 44 |
+
revision: null
|
| 45 |
+
scale_lr: false
|
| 46 |
+
seed: null
|
| 47 |
+
teacher_revision: null
|
| 48 |
+
tracker_project_name: text2image-fine-tune
|
| 49 |
+
train_batch_size: 4
|
| 50 |
+
train_shards_path_or_url: null
|
| 51 |
+
use_8bit_adam: true
|
| 52 |
+
use_fix_crop_and_size: false
|
| 53 |
+
validation_steps: 500000
|
| 54 |
+
w_max: 7.0
|
| 55 |
+
w_min: 6.0
|