Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,10 @@
-*.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
-*.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
-*.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
+*.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
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+datasets:
+  - "wikipedia"
+  
+tags:
+  - "arabic"
+  - "language-model"
+---
+
+# GPT2-Small-Arabic
+
+## Model description
+
+GPT2 model from Arabic Wikipedia dataset based on gpt2-small (using Fastai2).
+
+## Intended uses & limitations
+
+#### How to use
+
+An example is provided in this [colab notebook](https://colab.research.google.com/drive/1mRl7c-5v-Klx27EEAEOAbrfkustL4g7a?usp=sharing). 
+Both text and poetry (fine-tuned model) generation are included.
+
+#### Limitations and bias
+
+GPT2-small-arabic (trained on Arabic Wikipedia) has several limitations in terms of coverage (Arabic Wikipeedia quality, no diacritics) and training performance. 
+Use as demonstration or proof of concepts but not as production code.
+
+## Training data
+
+This pretrained model used the Arabic Wikipedia dump (around 900 MB). 
+
+## Training procedure
+
+Training was done using [Fastai2](https://github.com/fastai/fastai2/) library on Kaggle, using free GPU.
+
+## Eval results 
+Final perplexity reached was 72.19,  loss: 4.28, accuracy: 0.307
+
+### BibTeX entry and citation info
+
+```bibtex
+@inproceedings{Abed Khooli,
+  year={2020}
+}
+```

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": 50257
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b17fa39d5fb8a191151ed4b5f0fbbbbc030ee7b27afe86df05327f231ad3d3
+size 497764120

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378b7095b722fe85e599590d0c93aa106652c08fa3f136c506b6e61e7ac5892a
+size 510359598

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e554a02a5710d00ef5583d973adaa90f2128ed8f498f7a38bbb4bbde867c1e
+size 510378732

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"pad_token": "<|endoftext|>"}