Upload folder using huggingface_hub

README.md

@@ -199,4 +199,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
+- PEFT 0.13.2
 - PEFT 0.12.0

adapter_config.json

@@ -23,20 +23,20 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "to_v",
     "conv1",
-    "time_emb_proj",
-    "conv2",
-    "ff.net.2",
-    "ff.net.0.proj",
-    "to_out.0",
     "to_k",
     "conv_shortcut",
-    "to_q",
+    "proj_out",
     "downsamplers.0.conv",
+    "ff.net.0.proj",
     "upsamplers.0.conv",
-    "proj_out",
-    "proj_in",
-    "to_v"
+    "to_out.0",
+    "conv2",
+    "to_q",
+    "time_emb_proj",
+    "ff.net.2",
+    "proj_in"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb72effce4e2aae7020b1bb2e6b88d9d2bf77016d79af1559a1a652def46b92b
+oid sha256:be9a5a3924f6c964d31c486e1ccc4637aedc64f221f832dda7e74ec93ec96f46
 size 251887560

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: etri-vilab/koala-700m
+library_name: peft
+---
+
+# 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 0.13.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "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_v",
+    "conv1",
+    "to_k",
+    "conv_shortcut",
+    "proj_out",
+    "downsamplers.0.conv",
+    "ff.net.0.proj",
+    "upsamplers.0.conv",
+    "to_out.0",
+    "conv2",
+    "to_q",
+    "time_emb_proj",
+    "ff.net.2",
+    "proj_in"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9a5a3924f6c964d31c486e1ccc4637aedc64f221f832dda7e74ec93ec96f46
+size 251887560

checkpoint-200/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e64723557412a2ded999b7556a66aeee581cce1bb9e1b7ae014b2850558b5de
+size 128485884

checkpoint-200/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ec2e042e7130f8a83ef195434019172708f6a1f07c4fa1f796a31917abe2b1
+size 14408

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd55b3848d82967a207e0805911c79200c6adce71e3b37fd24549a718f75738
+size 988

checkpoint-200/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e5d7f11c268af031b89aac934fd3ff88222bc0b00e48552541527a2cb8920e
+size 1000

checkpoint-200/unet_lora/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb71fd957abc46778f7b4b5ffac76a4b3662d4f761cdefe7bb0e8a7b5875a14b
+size 251890168

logs/k7mlcmdistill-test/1729858058.488179/events.out.tfevents.1729858058.de8f3c3d4453.8958.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c9ecabfcfc2c6ae5eb7a18b6ecf609c119e904cd34d1830480480fc5b47f35
+size 2898

logs/k7mlcmdistill-test/1729858058.4900043/hparams.yml

@@ -0,0 +1,57 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0
+allow_tf32: false
+cache_dir: null
+cast_teacher_unet: false
+center_crop: false
+checkpointing_steps: 250
+checkpoints_total_limit: 10
+dataloader_num_workers: 2
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+huber_c: 0.001
+interpolation_type: bilinear
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lora_alpha: 64
+lora_dropout: 0.0
+lora_rank: 64
+lora_target_modules: null
+loss_type: huber
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: 4000000
+max_train_steps: 3250
+mixed_precision: fp16
+num_ddim_timesteps: 50
+num_train_epochs: 1
+output_dir: k7mlcmdistill-test
+pretrained_teacher_model: etri-vilab/koala-700m
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: null
+revision: null
+scale_lr: false
+seed: null
+teacher_revision: null
+timestep_scaling_factor: 10.0
+tracker_project_name: k7mlcmdistill-test
+train_batch_size: 1
+train_shards_path_or_url: /content/diffusers/examples/consistency_distillation/lart-1024-4000/00000.tar
+use_8bit_adam: true
+use_fix_crop_and_size: false
+vae_encode_batch_size: 8
+validation_steps: 10000000
+w_max: 15.0
+w_min: 3.0

logs/k7mlcmdistill-test/1729858155.550487/events.out.tfevents.1729858155.de8f3c3d4453.9433.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e2aaaeb08ce0f0e1bc98f178858fa1c3579001d206db1dc6eaa369dd0e581c
+size 2992

logs/k7mlcmdistill-test/1729858155.5524282/hparams.yml

@@ -0,0 +1,57 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0
+allow_tf32: false
+cache_dir: null
+cast_teacher_unet: false
+center_crop: false
+checkpointing_steps: 250
+checkpoints_total_limit: 10
+dataloader_num_workers: 2
+enable_xformers_memory_efficient_attention: true
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+huber_c: 0.001
+interpolation_type: bilinear
+learning_rate: 1.0e-05
+local_rank: -1
+logging_dir: logs
+lora_alpha: 64
+lora_dropout: 0.0
+lora_rank: 64
+lora_target_modules: null
+loss_type: huber
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_samples: 4000000
+max_train_steps: 3250
+mixed_precision: fp16
+num_ddim_timesteps: 50
+num_train_epochs: 1
+output_dir: k7mlcmdistill-test
+pretrained_teacher_model: etri-vilab/koala-700m
+pretrained_vae_model_name_or_path: null
+proportion_empty_prompts: 0
+push_to_hub: false
+random_flip: false
+report_to: tensorboard
+resolution: 1024
+resume_from_checkpoint: ./k7mlcmdistill-test/checkpoint-3000
+revision: null
+scale_lr: false
+seed: null
+teacher_revision: null
+timestep_scaling_factor: 10.0
+tracker_project_name: k7mlcmdistill-test
+train_batch_size: 1
+train_shards_path_or_url: /content/diffusers/examples/consistency_distillation/lart-1024-4000/00000.tar
+use_8bit_adam: true
+use_fix_crop_and_size: false
+vae_encode_batch_size: 8
+validation_steps: 10000000
+w_max: 15.0
+w_min: 3.0

logs/k7mlcmdistill-test/events.out.tfevents.1729858058.de8f3c3d4453.8958.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be49d91e4fbd62e6ac77932295f1ede0a45d047730b19b11d5212123f6348d89
+size 814

logs/k7mlcmdistill-test/events.out.tfevents.1729858155.de8f3c3d4453.9433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d002e1bf9c25eb7a01b0df47337ff1b5709853bf5a8ba32dca8a30da766e3b80
+size 340

unet_lora/pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4b7c170cb9bc6ee40c033e637e7b00525b25ceaf85bf1cc80acb77434c40ac
+oid sha256:cb71fd957abc46778f7b4b5ffac76a4b3662d4f761cdefe7bb0e8a7b5875a14b
 size 251890168