Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+library_name: transformers.js
+base_model:
+- microsoft/codebert-base
+pipeline_tag: feature-extraction
+---
+
+
+
+# codebert-base (ONNX)
+
+
+This is an ONNX version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base). It was automatically converted and uploaded using [this Hugging Face Space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
+
+
+## Usage with Transformers.js
+
+
+See the pipeline documentation for `feature-extraction`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.FeatureExtractionPipeline
+
+
+---
+
+
+## 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 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "microsoft/codebert-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eae0e839d13b948ced5195506504d430fdba45cdeef46cb3c8431490d573f98
+size 496505774

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c002e8c424052a3f4dd3af18b3683c37cc13cc3bd7a1391da565ffdf66ae32b
+size 204554096

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd9353afd6ce42038ee457627b8073fe075cd94d31955f67fc9e563cb4c5073a
+size 248395957

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac933da0ee18d1226228d23d68e6095e57370ab9be60269a69b9d98614e1ba6
+size 125207931

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e90cc1c8eb6b3e19b607111bc3a389ace33e13da8b8fd0c660d346c3f5ff2d
+size 209861984

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a64d00020466b35f4310acf8f77656b2849eb6bef57d99b8e97a2f713c9ba5a
+size 126313160

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac933da0ee18d1226228d23d68e6095e57370ab9be60269a69b9d98614e1ba6
+size 125207931

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150d04d7d76fced954f5e886feac5176de915dd64bb237f9a73177cadeabd698
+size 125207931

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}