Upload 11 files

.gitattributes

@@ -1,34 +1,18 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* 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
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz 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
+*.csv* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,246 @@
+---
+language: en
+tags:
+- seq2seq
+- t5
+- text-generation
+- recipe-generation
+pipeline_tag: text2text-generation
+widget:
+  - text: "provolone cheese, bacon, bread, ginger"
+  - text: "sugar, crunchy jif peanut butter, cornflakes"
+  - text: "sweet butter, confectioners sugar, flaked coconut, condensed milk, nuts, vanilla, dipping chocolate"
+  - text: "macaroni, butter, salt, bacon, milk, flour, pepper, cream corn"
+  - text: "hamburger, sausage, onion, regular, american cheese, colby cheese"
+  - text: "chicken breasts, onion, garlic, great northern beans, black beans, green chilies, broccoli, garlic oil, butter, cajun seasoning, salt, oregano, thyme, black pepper, basil, worcestershire sauce, chicken broth, sour cream, chardonnay wine"
+  - text: "serrano peppers, garlic, celery, oregano, canola oil, vinegar, water, kosher salt, salt, black pepper"
+---
+
+![avatar](chef-transformer.png)
+
+# Chef Transformer (T5) 
+> This is part of the
+[Flax/Jax Community Week](https://discuss.huggingface.co/t/recipe-generation-model/7475), organized by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
+
+Want to give it a try? Then what's the wait, head over to Hugging Face Spaces [here](https://huggingface.co/spaces/flax-community/chef-transformer).
+
+
+## Team Members
+- Mehrdad Farahani ([m3hrdadfi](https://huggingface.co/m3hrdadfi))
+- Kartik Godawat ([dk-crazydiv](https://huggingface.co/dk-crazydiv))
+- Haswanth Aekula ([hassiahk](https://huggingface.co/hassiahk))
+- Deepak Pandian ([rays2pix](https://huggingface.co/rays2pix))
+- Nicholas Broad ([nbroad](https://huggingface.co/nbroad))
+
+## Dataset
+
+[RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation](https://recipenlg.cs.put.poznan.pl/). This dataset contains **2,231,142** cooking recipes (>2 millions) with size of **2.14 GB**. It's processed in more careful way.
+
+### Example
+
+```json
+{
+  "NER": [
+    "oyster crackers",
+    "salad dressing",
+    "lemon pepper",
+    "dill weed",
+    "garlic powder",
+    "salad oil"
+  ],
+  "directions": [
+    "Combine salad dressing mix and oil.",
+    "Add dill weed, garlic powder and lemon pepper.",
+    "Pour over crackers; stir to coat.",
+    "Place in warm oven.",
+    "Use very low temperature for 15 to 20 minutes."
+  ],
+  "ingredients": [
+    "12 to 16 oz. plain oyster crackers",
+    "1 pkg. Hidden Valley Ranch salad dressing mix",
+    "1/4 tsp. lemon pepper",
+    "1/2 to 1 tsp. dill weed",
+    "1/4 tsp. garlic powder",
+    "3/4 to 1 c. salad oil"
+  ],
+  "link": "www.cookbooks.com/Recipe-Details.aspx?id=648947",
+  "source": "Gathered",
+  "title": "Hidden Valley Ranch Oyster Crackers"
+}
+```
+
+## How To Use
+
+```bash
+# Installing requirements
+pip install transformers
+```
+
+```python
+from transformers import FlaxAutoModelForSeq2SeqLM
+from transformers import AutoTokenizer
+
+MODEL_NAME_OR_PATH = "flax-community/t5-recipe-generation"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME_OR_PATH, use_fast=True)
+model = FlaxAutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME_OR_PATH)
+
+prefix = "items: "
+# generation_kwargs = {
+#     "max_length": 512,
+#     "min_length": 64,
+#     "no_repeat_ngram_size": 3,
+#     "early_stopping": True,
+#     "num_beams": 5,
+#     "length_penalty": 1.5,
+# }
+generation_kwargs = {
+    "max_length": 512,
+    "min_length": 64,
+    "no_repeat_ngram_size": 3,
+    "do_sample": True,
+    "top_k": 60,
+    "top_p": 0.95
+}
+
+
+special_tokens = tokenizer.all_special_tokens
+tokens_map = {
+    "<sep>": "--",
+    "<section>": "\n"
+}
+def skip_special_tokens(text, special_tokens):
+    for token in special_tokens:
+        text = text.replace(token, "")
+
+    return text
+
+def target_postprocessing(texts, special_tokens):
+    if not isinstance(texts, list):
+        texts = [texts]
+    
+    new_texts = []
+    for text in texts:
+        text = skip_special_tokens(text, special_tokens)
+
+        for k, v in tokens_map.items():
+            text = text.replace(k, v)
+
+        new_texts.append(text)
+
+    return new_texts
+
+def generation_function(texts):
+    _inputs = texts if isinstance(texts, list) else [texts]
+    inputs = [prefix + inp for inp in _inputs]
+    inputs = tokenizer(
+        inputs, 
+        max_length=256, 
+        padding="max_length", 
+        truncation=True, 
+        return_tensors="jax"
+    )
+
+    input_ids = inputs.input_ids
+    attention_mask = inputs.attention_mask
+
+    output_ids = model.generate(
+        input_ids=input_ids, 
+        attention_mask=attention_mask,
+        **generation_kwargs
+    )
+    generated = output_ids.sequences
+    generated_recipe = target_postprocessing(
+        tokenizer.batch_decode(generated, skip_special_tokens=False),
+        special_tokens
+    )
+    return generated_recipe
+```
+
+```python
+items = [
+    "macaroni, butter, salt, bacon, milk, flour, pepper, cream corn",
+    "provolone cheese, bacon, bread, ginger"
+]
+generated = generation_function(items)
+for text in generated:
+    sections = text.split("\n")
+    for section in sections:
+        section = section.strip()
+        if section.startswith("title:"):
+            section = section.replace("title:", "")
+            headline = "TITLE"
+        elif section.startswith("ingredients:"):
+            section = section.replace("ingredients:", "")
+            headline = "INGREDIENTS"
+        elif section.startswith("directions:"):
+            section = section.replace("directions:", "")
+            headline = "DIRECTIONS"
+        
+        if headline == "TITLE":
+            print(f"[{headline}]: {section.strip().capitalize()}")
+        else:
+            section_info = [f"  - {i+1}: {info.strip().capitalize()}" for i, info in enumerate(section.split("--"))]
+            print(f"[{headline}]:")
+            print("\n".join(section_info))
+
+    print("-" * 130)
+```
+
+Output:
+```text
+[TITLE]: Macaroni and corn
+[INGREDIENTS]:
+  - 1: 2 c. macaroni
+  - 2: 2 tbsp. butter
+  - 3: 1 tsp. salt
+  - 4: 4 slices bacon
+  - 5: 2 c. milk
+  - 6: 2 tbsp. flour
+  - 7: 1/4 tsp. pepper
+  - 8: 1 can cream corn
+[DIRECTIONS]:
+  - 1: Cook macaroni in boiling salted water until tender.
+  - 2: Drain.
+  - 3: Melt butter in saucepan.
+  - 4: Blend in flour, salt and pepper.
+  - 5: Add milk all at once.
+  - 6: Cook and stir until thickened and bubbly.
+  - 7: Stir in corn and bacon.
+  - 8: Pour over macaroni and mix well.
+----------------------------------------------------------------------------------------------------------------------------------
+[TITLE]: Grilled provolone and bacon sandwich
+[INGREDIENTS]:
+  - 1: 2 slices provolone cheese
+  - 2: 2 slices bacon
+  - 3: 2 slices sourdough bread
+  - 4: 2 slices pickled ginger
+[DIRECTIONS]:
+  - 1: Place a slice of provolone cheese on one slice of bread.
+  - 2: Top with a slice of bacon.
+  - 3: Top with a slice of pickled ginger.
+  - 4: Top with the other slice of bread.
+  - 5: Heat a skillet over medium heat.
+  - 6: Place the sandwich in the skillet and cook until the cheese is melted and the bread is golden brown.
+----------------------------------------------------------------------------------------------------------------------------------
+```
+
+## Evaluation
+Since the test set is not available, we will evaluate the model based on a shared test set. This test set consists of 5% of the whole test (*= 5,000 records*), 
+and we will generate five recipes for each input(*= 25,000 records*). 
+The following table summarizes the scores obtained by the **Chef Transformer** and **RecipeNLG** as our baseline.
+
+|                                   Model                                  |    COSIM   |     WER    |   ROUGE-2  |    BLEU    |    GLEU    |   METEOR   |
+|:------------------------------------------------------------------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|
+|            [RecipeNLG](https://huggingface.co/mbien/recipenlg)           |   0.5723   |   1.2125   |   0.1354   |   0.1164   |   0.1503   |   0.2309   |
+| [Chef Transformer](huggingface.co/flax-community/t5-recipe-generation) * | **0.7282** | **0.7613** | **0.2470** | **0.3245** | **0.2624** | **0.4150** |
+
+*From the 5 generated recipes corresponding to each NER (food items), only the highest score was taken into account in the WER, COSIM, and ROUGE metrics. At the same time, BLEU, GLEU, Meteor were designed to have many possible references.*
+
+
+## Copyright
+
+Special thanks to those who provided these fantastic materials.
+- [Anatomy](https://www.flaticon.com/free-icon)
+- [Chef Hat](https://www.vecteezy.com/members/jellyfishwater)
+- [Moira Nazzari](https://pixabay.com/photos/food-dessert-cake-eggs-butter-3048440/)
+- [Instagram Post](https://www.freepik.com/free-psd/recipes-ad-social-media-post-template_11520617.htm)

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    },
+    "text2text-generation": {
+      "early_stopping": true,
+      "max_length": 512,
+      "repetition_penalty": 1.2,
+      "length_penalty": 1.2,
+      "num_beams": 5,
+      "prefix": "items: "
+    }
+  },
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

events.out.tfevents.1625725210.t1v-n-a0c138ef-w-0.183348.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ddf08cb1bf3c10e07a056dd0cf7050d92c3835b947812877ef872a76156f460
+size 20265157

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effb0d06380db9445a71a59885bb5006bf40eddd781b54a32da1efe0f154fc57
+size 891625348

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637cc03a65c7ab9b1798e0ea03e6cd3909e278b1e441b2bc85a6eb3380607919
+size 891727295

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0d107670b05c104f606fe6aca353bf17be0e58c24b683b8e44163336dbf68d
+size 892144216

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}