initial commit

README.md

@@ -0,0 +1,36 @@
+---
+language: ar
+---
+
+# Dialect-AR-GPT-2021
+## Finetuned AraGPT-2 demo
+
+This model started with [AraGPT2-Medium](https://huggingface.co/aubmindlab/aragpt2-medium),
+from AUB MIND Lab.
+
+This model was then finetuned on dialect datasets from Qatar University, University of British Columbia / NLP,
+and Johns Hopkins University / LREC for 10 epochs.
+
+Sources
+- https://qspace.qu.edu.qa/handle/10576/15265
+- https://github.com/UBC-NLP/aoc_id
+- https://github.com/ryancotterell/arabic_dialect_annotation
+
+You can use special tokens to prompt five dialects: `[EGYPTIAN]`, `[GULF]`, `[LEVANTINE]`, `[MAGHREBI]`, or `[MSA]`, followed by a space.
+
+```
+from simpletransformers.language_generation import LanguageGenerationModel
+model = LanguageGenerationModel("gpt2", "monsoon-nlp/dialect-ar-gpt-2021")
+model.generate('[GULF] ' + "مدينتي هي", { 'max_length': 100 })
+```
+
+There is NO content filtering in the current version; do not use for public-facing
+text generation!
+
+## Training and Finetuning details
+
+Original model: https://huggingface.co/aubmindlab/aragpt2-medium
+
+I inserted new tokens into the tokenizer, finetuned the model on the dialect samples, and exported the new model.
+
+Notebook: https://colab.research.google.com/drive/19C0zbkSCt5ncVCa4kY-ik9hSEiJcjI-F

added_tokens.json

@@ -0,0 +1 @@
+{"[EGYPTIAN]": 64000, "[MSA]": 64001, "[LEVANTINE]": 64002, "[GULF]": 64003, "[MAGHREBI]": 64004}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "aubmindlab/aragpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "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,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "repetition_penalty": 3.0,
+      "top_p": 0.95
+    }
+  },
+  "transformers_version": "4.2.2",
+  "use_cache": true,
+  "vocab_size": 64005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db195f4e6cd087e21715def19e516c376d2b9c5ba5e48f2905d170633a8efd0
+size 1500897917

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "tokenizer_file": "cache_dir/984b9be0ec2b726074332b6c59e66d89049f148f96160849e6e5a9bdd7bc97b2.6ce583b24c6d3225d59bf6fb3ac34ead1e0fa04af22fb464906ee74d4c25bd77", "name_or_path": "aubmindlab/aragpt2-medium"}