Upload 10 files

README.md

@@ -1,3 +1,27 @@
----
-license: apache-2.0
----
+## CodeBERT-base
+Pretrained weights for [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://arxiv.org/abs/2002.08155).
+
+### Training Data
+The model is trained on bi-modal data (documents & code) of [CodeSearchNet](https://github.com/github/CodeSearchNet)
+
+### Training Objective
+This model is initialized with Roberta-base and trained with MLM+RTD objective (cf. the paper).
+
+### Usage
+Please see [the official repository](https://github.com/microsoft/CodeBERT) for scripts that support "code search" and "code-to-document generation".
+
+### Reference
+1. [CodeBERT trained with Masked LM objective](https://huggingface.co/microsoft/codebert-base-mlm) (suitable for code completion)
+2. 🤗 [Hugging Face's CodeBERTa](https://huggingface.co/huggingface/CodeBERTa-small-v1) (small size, 6 layers)
+
+### Citation
+```bibtex
+@misc{feng2020codebert,
+    title={CodeBERT: A Pre-Trained Model for Programming and Natural Languages},
+    author={Zhangyin Feng and Daya Guo and Duyu Tang and Nan Duan and Xiaocheng Feng and Ming Gong and Linjun Shou and Bing Qin and Ting Liu and Daxin Jiang and Ming Zhou},
+    year={2020},
+    eprint={2002.08155},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3070d54e9a6582a500785a53f40a838269d13cdf6a27711037580fed717bcd
+size 498589677

gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91362f5a5a4dd0b1f96c7c4d2ebc512c00b834d501a2612d1f12f6ab4ca5535
+size 498644338

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cb3355c7c32f42e3d97b0a0dc5b73c944305b9ece419170ec62f78c525d8e0
+size 498845224

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}