Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+library_name: transformers.js
+base_model:
+- neulab/codebert-javascript
+pipeline_tag: fill-mask
+---
+
+
+
+# codebert-javascript (ONNX)
+
+
+This is an ONNX version of [neulab/codebert-javascript](https://huggingface.co/neulab/codebert-javascript). 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 `fill-mask`: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.FillMaskPipeline
+
+
+---
+
+
+This is a `microsoft/codebert-base-mlm` model, trained for 1,000,000 steps (with `batch_size=32`)  on **JavaScript** code from the `codeparrot/github-code-clean` dataset, on the masked-language-modeling task.
+
+It is intended to be used in CodeBERTScore: [https://github.com/neulab/code-bert-score](https://github.com/neulab/code-bert-score), but can be used for any other model or task.
+
+For more information, see: [https://github.com/neulab/code-bert-score](https://github.com/neulab/code-bert-score)
+
+## Citation
+
+If you use this model for research, please cite:
+```
+@article{zhou2023codebertscore,
+  url = {https://arxiv.org/abs/2302.05527},
+  author = {Zhou, Shuyan and Alon, Uri and Agarwal, Sumit and Neubig, Graham},
+  title = {CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code},  
+  publisher = {arXiv},
+  year = {2023},
+}
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "neulab/codebert-javascript",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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:cfac6324e801e975d1bc0da5750d85bd52fd0507288b0253b0c4b1c95d7bfa15
+size 498915716

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3325ff81af28b267c356c3eef25300de0e3207e277e70234238882c25df426
+size 204936673

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef1592f78e6ee0690a36b9db9c98b610d45dc04f405a3319db37ae0b1a326f3
+size 249621682

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e876ede9983f7ce2013fdbf673a91994a0792597b26d3fc40ae682f338902d4
+size 125862157

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a2772513b7a9bdfc62ff41724c4f448ab4e64529f8f927bcfb5d2571a34033
+size 210281418

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39ca351eebe6216be035717236ab27e00c823a9d170696cd56a52fc9a57ee99
+size 126691163

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e876ede9983f7ce2013fdbf673a91994a0792597b26d3fc40ae682f338902d4
+size 125862157

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeb6ff30bb5e375c60d6be3a148beca1ad555aac3c5393373ba8579fa828557
+size 125862157

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "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>"
+}