Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: kmpartner/k512-ft-test
 library_name: peft
+base_model: kmpartner/k512-ft-test
 ---
 
 # Model Card for Model ID
@@ -199,5 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
+- PEFT 0.9.0
 - PEFT 0.15.2
 - PEFT 0.14.0

adapter_config.json

@@ -6,18 +6,13 @@
   },
   "base_model_name_or_path": null,
   "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
-  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 8,
-  "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -27,23 +22,22 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "to_out.0",
     "upsamplers.0.conv",
-    "to_k",
-    "time_emb_proj",
-    "proj_in",
-    "conv1",
+    "conv_shortcut",
+    "conv2",
     "proj_out",
     "ff.net.0.proj",
+    "ff.net.2",
+    "to_k",
+    "conv1",
+    "time_emb_proj",
     "to_q",
     "downsamplers.0.conv",
     "to_v",
-    "ff.net.2",
-    "conv_shortcut",
-    "conv2",
-    "to_out.0"
+    "proj_in"
   ],
   "task_type": null,
-  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0955c9d96ab8cd3bf4b9b177e77ae2e7944c357f7dcf8b9766651799b1e04f8
+oid sha256:c41444bbbe0bb6d8985fdb54ccc7f60c9e1f9d64eb5fc31411ca6a94a2686c0e
 size 251887560

checkpoint-14750/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: kmpartner/k512-ft-test
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

checkpoint-14750/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "UNet2DConditionModel",
+    "parent_library": "diffusers.models.unets.unet_2d_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "upsamplers.0.conv",
+    "conv_shortcut",
+    "conv2",
+    "proj_out",
+    "ff.net.0.proj",
+    "ff.net.2",
+    "to_k",
+    "conv1",
+    "time_emb_proj",
+    "to_q",
+    "downsamplers.0.conv",
+    "to_v",
+    "proj_in"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-14750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41444bbbe0bb6d8985fdb54ccc7f60c9e1f9d64eb5fc31411ca6a94a2686c0e
+size 251887560

checkpoint-14750/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e3c68cf7bb5d3945bd2c243eff9391997cdceb4ccfaabcf0e7b92375a653cba
+size 129845198

checkpoint-14750/optimizer_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9b9669047114d8f2e747b0d9958e0b635938e2bf75e4091e63ec449a985ad7
+size 8898746

checkpoint-14750/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48cb0a77fafc3d545a197e0cd61f10009cff0b54f2819366383b9241ee58795
+size 14408

checkpoint-14750/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded3fd1783f3a67ff31e8a0f8331f1c11dc22a8f4e13b0613c7315c6daf737a0
+size 988

checkpoint-14750/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1be9efeb7cd9df76fa908279de81b9831038cba2e407077a24ce2226ba6572
+size 1000

checkpoint-14750/unet_lora/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55515543ced38cf4a7045b647447fd47ed83b8b2a6f69e5956ac98c5d9026ddc
+size 251890168

logs/text2image-fine-tune/1748001329.4313157/events.out.tfevents.1748001329.048cbd8baefc.3793.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd603d9aba5ef6f64fce1be4b20433f337895e97354619e2f34c279c5fb41460
+size 2841

logs/text2image-fine-tune/1748001329.4335504/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0
+adv_lr: 1.0e-05
+adv_weight: 0.1
+allow_tf32: true
+cache_dir: null
+cast_teacher_unet: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: 10
+dataloader_num_workers: 1
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+huber_c: 0.001
+learning_rate: 2.0e-06
+local_rank: -1
+logging_dir: logs
+lora_rank: 64
+loss_type: huber
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 4000000
+max_train_steps: 15000
+mixed_precision: fp16
+multiphase: 1
+not_apply_cfg_solver: false
+num_ddim_timesteps: 40
+num_train_epochs: 30
+output_dir: k5pcmlra-test
+pretrained_teacher_model: etri-vilab/koala-700m
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+proportion_empty_prompts: 0
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: checkpoint-14500
+revision: null
+scale_lr: false
+seed: null
+teacher_revision: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 16
+train_shards_path_or_url: null
+use_8bit_adam: true
+use_fix_crop_and_size: false
+validation_steps: 500000
+w_max: 7.0
+w_min: 6.0

logs/text2image-fine-tune/1748003773.598279/events.out.tfevents.1748003773.048cbd8baefc.14728.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8d2fc0a0dc5f91f39446b0c816f357738583a22c0b24cb82ac0d4fb37c5168
+size 2841

logs/text2image-fine-tune/1748003773.6007702/hparams.yml

@@ -0,0 +1,55 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0
+adv_lr: 1.0e-05
+adv_weight: 0.1
+allow_tf32: true
+cache_dir: null
+cast_teacher_unet: false
+center_crop: false
+checkpointing_steps: 250
+checkpoints_total_limit: 10
+dataloader_num_workers: 1
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+huber_c: 0.001
+learning_rate: 2.0e-06
+local_rank: -1
+logging_dir: logs
+lora_rank: 64
+loss_type: huber
+lr_scheduler: constant
+lr_warmup_steps: 500
+max_grad_norm: 1.0
+max_train_samples: 4000000
+max_train_steps: 14750
+mixed_precision: fp16
+multiphase: 1
+not_apply_cfg_solver: false
+num_ddim_timesteps: 40
+num_train_epochs: 59
+output_dir: k5pcmlra-test
+pretrained_teacher_model: etri-vilab/koala-700m
+pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
+proportion_empty_prompts: 0
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: checkpoint-14500
+revision: null
+scale_lr: false
+seed: null
+teacher_revision: null
+tracker_project_name: text2image-fine-tune
+train_batch_size: 8
+train_shards_path_or_url: null
+use_8bit_adam: true
+use_fix_crop_and_size: false
+validation_steps: 500000
+w_max: 7.0
+w_min: 6.0

logs/text2image-fine-tune/events.out.tfevents.1748001329.048cbd8baefc.3793.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebaa7bf91a8c2f0e19959176c1272ee46b6858dc642d126d55c9808eb407c7b
+size 5320

logs/text2image-fine-tune/events.out.tfevents.1748003773.048cbd8baefc.14728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2405a2657bf3a76bb8004d589994254ee3817e062970438cd3350d0f16b4273d
+size 27338

unet_lora/pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c65807faab8aff95fc8ea202637bc801ee2b16c893bb82b2ba3477d9123e87
+oid sha256:55515543ced38cf4a7045b647447fd47ed83b8b2a6f69e5956ac98c5d9026ddc
 size 251890168