Initial upload

README.md

@@ -0,0 +1,11 @@
+# RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation
+
+Model accompanying our INLG 2020 paper: [RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation](https://www.aclweb.org/anthology/2020.inlg-1.4.pdf)
+
+## Where is the dataset?
+
+Please visit the website of our project: [recipenlg.cs.put.poznan.pl](https://recipenlg.cs.put.poznan.pl/) to download it.
+
+## How to use the model? Could you explain X andy Y?
+
+Yes, sure! If you feel some information is missing in our paper, please check first in our [thesis](https://www.researchgate.net/publication/345308878_Cooking_recipes_generator_utilizing_a_deep_learning-based_language_model), which is much more detailed. In case of further questions, you're invited to send us a github issue, we will respond as fast as we can!

added_tokens.json

@@ -0,0 +1 @@
+{"<TITLE_START>": 50257, "<TITLE_END>": 50258, "<INSTR_START>": 50259, "<NEXT_INSTR>": 50260, "<INSTR_END>": 50261, "<INGR_START>": 50262, "<NEXT_INGR>": 50263, "<INGR_END>": 50264, "<RECIPE_START>": 50265, "<RECIPE_END>": 50266, "<INPUT_START>": 50267, "<INPUT_END>": 50268, "<NEXT_INPUT>": 50269}

config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "vocab_size": 50270
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8b027c2e17a211f9c47059ae8dd48d7160f6076b12795399dac9d31ed79750
+size 664846605

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "additional_special_tokens": ["<TITLE_START>", "<TITLE_END>", "<INSTR_START>", "<NEXT_INSTR>", "<INSTR_END>", "<INGR_START>", "<NEXT_INGR>", "<INGR_END>", "<RECIPE_START>", "<RECIPE_END>", "<INPUT_START>", "<INPUT_END>", "<NEXT_INPUT>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}