Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+onnx/model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+language: en
+license: apache-2.0
+library_name: transformers.js
+pipeline_tag: token-classification
+tags:
+  - grammatical-error-correction
+  - gector
+  - onnx
+  - transformers.js
+---
+
+# GECToR Base 2020 (ONNX)
+
+ONNX quantized version of the original GECToR model from Grammarly for browser-based grammatical error correction with [Transformers.js](https://huggingface.co/docs/transformers.js).
+
+## Original Model
+
+- **Source**: [Grammarly GECToR](https://github.com/grammarly/gector)
+- **Paper**: [GECToR – Grammatical Error Correction: Tag, Not Rewrite](https://arxiv.org/abs/2005.12592) (BEA Workshop 2020)
+- **Architecture**: RoBERTa-Base + token classification head
+- **Parameters**: ~125M
+
+## Conversion Details
+
+- **Format**: ONNX
+- **Quantization**: INT8 (dynamic quantization)
+- **Size**: ~125MB
+- **Converted by**: Manual export from PyTorch (AllenNLP format)
+
+## How It Works
+
+GECToR uses a token classification approach - instead of generating corrected text, it predicts edit operations for each token:
+
+- `$KEEP` - Keep token unchanged
+- `$DELETE` - Remove token
+- `$REPLACE_word` - Replace with specific word
+- `$APPEND_word` - Append word after token
+- `$TRANSFORM_*` - Apply transformation (case, verb form, etc.)
+
+The model runs iteratively (typically 2-3 passes) until no more edits are predicted.
+
+## Usage with Transformers.js
+
+```javascript
+import { pipeline } from '@huggingface/transformers';
+
+const classifier = await pipeline(
+  'token-classification',
+  'YOUR_USERNAME/gector-base-2020',
+  { dtype: 'q8' }
+);
+
+const result = await classifier('He go to school yesterday.');
+// Returns token predictions with edit tags
+```
+
+## Performance
+
+Faster than the 2024 version with slightly lower accuracy. Good balance of speed and quality.
+
+## License
+
+Apache 2.0 (following original model license)

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5dbe89d72d01afc610e69dd0060028f1106b3cf320193fe391cc1357db0371
+size 1568349

onnx/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca83094f3558a0f7e25c2c8d0d1f07a802e589c11b039d949d7ed02130ff9ca
+size 511719424

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ced3d80b1e06d610ff83104b2f4b8a3919f21b8e70120556526de314658426
+size 129688821

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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>"
+}