Super-squash branch 'main' using huggingface_hub

Co-authored-by: SFconvertbot <SFconvertbot@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,101 @@
+---
+license: other
+tags:
+- generated_from_trainer
+- text generation
+- stable diffusion
+- midjourney
+- text2image
+- text to image
+- prompt augment
+- prompt engineering
+thumbnail: https://i.imgur.com/DeKNHtC.jpg
+datasets:
+- pszemraj/text2image-multi-prompt
+widget:
+ - text: "morning sun over Jakarta"
+   example_title: "morning sun"
+ - text: "WARNING: pip is"
+   example_title: "pip"
+ - text: "sentient cheese"
+   example_title: "sentient cheese"
+ - text: "cheeps are"
+   example_title: "cheeps"
+ - text: "avocado armchair"
+   example_title: "creative prompt"
+ - text: "Landscape of"
+   example_title: "landscape"
+parameters:
+  min_length: 16
+  max_length: 96
+  no_repeat_ngram_size: 1
+  do_sample: True
+---
+
+
+# pszemraj/opt-350m-multiprompt
+
+<a href="https://colab.research.google.com/gist/pszemraj/bdd1238ee4b8330aeec6774a16f9a677/opt-350m-multiprompt-demo.ipynb">
+  <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
+</a>
+
+Generate/augment your prompt with a model trained on a large & diverse prompt dataset.
+
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the pszemraj/text2image-prompts-multi dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6669
+- eval steps per second: 16.21
+- perplexity: 5.29
+
+## Example
+
+
+![landscape of florida](https://i.imgur.com/DeKNHtC.jpg)
+
+<br>
+
+_The above example was created with [DALL-E 2](https://labs.openai.com/sc/YbiY2kkuQeODzHNwUHn4D5RN) but will of course work with any text2image model._
+
+## Intended uses & limitations
+
+- The model will generate augmentations that are biased towards the training data, i.e. what people already asked for in the SD/midjourney discords, etc. Creating a larger dataset was an attempt at mitigating this through more data from different datasets.
+
+## Training and evaluation data
+
+See the `pszemraj/text2image-prompts-multi` dataset card for details. The dataset is a compilation of several text-to-image prompt datasets on huggingface  :)
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 256
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.04
+- num_epochs: 4.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.1677        | 1.0   | 990  | 2.0888          |
+| 1.856         | 2.0   | 1980 | 1.8215          |
+| 1.6864        | 3.0   | 2970 | 1.6935          |
+| 1.6228        | 4.0   | 3960 | 1.6670          |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "no_repeat_ngram_size": 2,
+      "repetition_penalty": 4.5,
+      "max_length": 48
+    }
+  },
+  "word_embed_proj_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.6668897867202759,
+    "eval_runtime": 102.7014,
+    "eval_samples": 13319,
+    "eval_samples_per_second": 129.687,
+    "eval_steps_per_second": 16.212,
+    "perplexity": 5.295671489170355
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57c49cdb01dc9557f4455094d76c12c2ec4030d8aed0784501af7b7f0b611f5
+size 662438164

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743eb512852251be08a75f53fcbdc54da6810c302f91b9f948513d6064ebc538
+size 662524445

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "name_or_path": "facebook/opt-350m",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 1.9931427570304485,
+    "train_runtime": 30194.781,
+    "train_samples": 253694,
+    "train_samples_per_second": 33.608,
+    "train_steps_per_second": 0.131
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017f65ad7bf3b0edcc77f94ff61fa646a524820ede2792c36a5ba61057311c70
+size 3387