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 +1,106 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- alpaca
+- self-instruct
+- instruction generation
+- instructiongen
+- longform 
+- prompt-generation
+metrics:
+- rouge
+datasets:
+- akoksal/LongForm
+- pszemraj/fleece2instructions
+widget:
+- text: >-
+    You'll need to start by choosing the right venue. Consider the type of
+    atmosphere and the size of the area that will be suitable for the number of
+    guests you plan to invite. Choose the right decorations based on your
+    brother's interests, such as balloons in his favorite colors, banners, and
+    streamers. Next, decide on the food and drinks, making sure they are tasty
+    and appropriate for the occasion. Then decide on the other games, music, and
+    entertainment that will make the party memorable. Finally, involve your
+    brother's friends and family to help create the perfect surprise.
+  example_title: birthday party
+- text: 1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo
+  example_title: ice cream
+- text: >-
+    Start by selecting a scale model of a building that fits the theme. Use a
+    hobby knife and glue to cut and assemble the model into a ruined or
+    abandoned version of itself, adding details like broken windows and
+    graffiti. Create a base for the diorama using foam, plaster, or other
+    materials, and paint it to resemble a ruined street or sidewalk. Add
+    miniature vehicles, debris, and figures to complete the scene, and use
+    weathering techniques like dry brushing and rust washes to add realism.
+    Display the diorama in a shadow box or other protective case to showcase
+    your work.
+  example_title: Miniature diorama creation
+- text: >-
+    Start by selecting clothing that is futuristic and edgy, such as leather
+    jackets, neon-colored accessories, and tech-inspired patterns. Add
+    accessories like goggles, cybernetic implants, and LED lights to enhance the
+    cyberpunk vibe. Use makeup and body paint to create a futuristic look, such
+    as metallic skin or neon makeup. Consider adding functional elements to your
+    costume, such as a built-in backpack or hidden pockets for your tech
+    gadgets. Finally, practice your confident walk and embrace your inner
+    cyberpunk for a memorable and immersive costume experience.
+  example_title: Cyberpunk costume design
+- text: >-
+    Start by creating a base terrain with mountains, valleys, and other natural
+    features. Use fractal noise and displacement mapping to add texture and
+    detail to the terrain, and experiment with different materials like rock,
+    grass, and water. Add surreal elements like floating islands, giant
+    mushrooms, or impossible geometry to create a dreamlike atmosphere. Use
+    lighting and color grading to enhance the mood and tone of the scene, and
+    render the final image at a high resolution for maximum impact. Share your
+    surreal landscape with the world and inspire others to explore the
+    possibilities of 3D art.
+  example_title: Surreal 3D landscape creation
+- text: >-
+    Start by setting a realistic goal and creating a training plan. Build up
+    your mileage gradually over time, and incorporate cross-training and
+    strength exercises to prevent injury and improve endurance. Be sure to stay
+    hydrated and properly fuel your body with nutritious foods. Listen to your
+    body and adjust your training as needed to avoid overexertion or burnout.
+    Finally, taper your training in the weeks leading up to the race to give
+    your body time to rest and recover before the big day.
+  example_title: Marathon training
+inference:
+  parameters:
+    max_length: 96
+    num_beams: 4
+---
+
+
+# bart-base-instructiongen + LongForm
+
+Instead of generating questions from text, generate instructions for LLMs! 
+
+- Check out a [basic demo on Spaces](https://huggingface.co/spaces/pszemraj/generate-instructions)
+- An example of how to use instructiongen models in a CLI script can be found [here](https://gist.github.com/pszemraj/8b0213e700763106074d3ac15d041c14)
+- You can find other models fine-tuned for instruction generation by [searching for the instructiongen tag](https://huggingface.co/models?other=instructiongen).
+
+## about
+
+This model is a fine-tuned version of [pszemraj/bart-base-instructiongen](https://huggingface.co/pszemraj/bart-base-instructiongen) on the `akoksal/LongForm` dataset.
+
+This was trained on a dataset of **only** instructions+outputs, with any `inputs` filtered out. This means that text of *1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo* will **not** get you *"Rank the following ice cream flavors: oreo, mint chip, chocolate chip, cookies and cream"*.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.02
+- num_epochs: 3.0

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "pszemraj/bart-base-instructiongen",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ec5da5c132087567425ea0521eb5db86225af8956ec11ff316eb28e5dd53d0
+size 557912620

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f346717b0be73ec240d71c865e34ba2caf7cd9c9c5cf2235e5fa180b6cb6448f
+size 557971229

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e61fa7bb8d66fb50f9693021c17fd04ad818ce50b98f34f3a28a6fcca8fc545
+size 4155