Add UniXcoder ONNX model for Transformers.js

README.md

@@ -0,0 +1,128 @@
+---
+language:
+  - en
+  - code
+license: apache-2.0
+library_name: transformers.js
+tags:
+  - code
+  - embeddings
+  - onnx
+  - transformers.js
+  - semantic-search
+  - code-search
+pipeline_tag: feature-extraction
+base_model: microsoft/unixcoder-base
+---
+
+# UniXcoder ONNX for Code Search
+
+**Converted by [VibeAtlas](https://vibeatlas.dev)** - AI Context Optimization for Developers
+
+This is [Microsoft's UniXcoder](https://huggingface.co/microsoft/unixcoder-base) converted to ONNX format for use with **Transformers.js** in browser and Node.js environments.
+
+## Why UniXcoder?
+
+UniXcoder understands code **semantically**, not just as text:
+- Trained on 6 programming languages (Python, Java, JavaScript, PHP, Ruby, Go)
+- Understands AST structure and data flow
+- 20-30% better code search accuracy vs generic embedding models
+
+## Quick Start
+
+### Transformers.js (Browser/Node.js)
+
+```javascript
+import { pipeline } from '@huggingface/transformers';
+
+const embedder = await pipeline(
+  'feature-extraction',
+  'sailesh27/unixcoder-base-onnx'
+);
+
+const code = `function authenticate(user) {
+  return user.isValid && user.hasPermission;
+}`;
+
+const embedding = await embedder(code, {
+  pooling: 'mean',
+  normalize: true
+});
+
+console.log(embedding.dims); // [1, 768]
+```
+
+### Semantic Code Search
+
+```javascript
+import { pipeline, cos_sim } from '@huggingface/transformers';
+
+const embedder = await pipeline('feature-extraction', 'sailesh27/unixcoder-base-onnx');
+
+// Index your code
+const codeSnippets = [
+  'function login(user, pass) { ... }',
+  'function formatDate(date) { ... }',
+  'function validateEmail(email) { ... }'
+];
+
+const codeEmbeddings = await embedder(codeSnippets, { pooling: 'mean', normalize: true });
+
+// Search with natural language
+const query = 'user authentication';
+const queryEmbedding = await embedder(query, { pooling: 'mean', normalize: true });
+
+// Find most similar
+const similarities = codeEmbeddings.tolist().map((emb, i) => ({
+  code: codeSnippets[i],
+  score: cos_sim(queryEmbedding.tolist()[0], emb)
+}));
+```
+
+## Technical Details
+
+- **Architecture**: RoBERTa-based encoder
+- **Hidden Size**: 768
+- **Max Sequence Length**: 512 tokens
+- **Output Dimensions**: 768
+- **ONNX Opset**: 14
+
+## About VibeAtlas
+
+**VibeAtlas** is the reliability infrastructure for AI coding:
+
+- Reduce AI token costs by 40-60%
+- Improve code search accuracy with semantic understanding
+- Add governance guardrails to AI workflows
+
+**Links**:
+- [Website](https://vibeatlas.dev)
+- [VS Code Extension](https://marketplace.visualstudio.com/items?itemName=vibeatlas.vibeatlas)
+- [GitHub](https://github.com/vibeatlas)
+
+## Citation
+
+```bibtex
+@misc{unixcoder-onnx-2025,
+  title={UniXcoder ONNX: Code Embeddings for JavaScript},
+  author={VibeAtlas Team},
+  year={2025},
+  publisher={Hugging Face},
+  url={https://huggingface.co/sailesh27/unixcoder-base-onnx}
+}
+```
+
+### Original UniXcoder Paper
+
+```bibtex
+@inproceedings{guo2022unixcoder,
+  title={UniXcoder: Unified Cross-Modal Pre-training for Code Representation},
+  author={Guo, Daya and Lu, Shuai and Duan, Nan and Wang, Yanlin and Zhou, Ming and Yin, Jian},
+  booktitle={ACL},
+  year={2022}
+}
+```
+
+## License
+
+Apache 2.0 (same as original UniXcoder)

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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": 1026,
+  "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": "4.55.4",
+  "type_vocab_size": 10,
+  "use_cache": true,
+  "vocab_size": 51416
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7c6027c122832f0b416c1956739bf79e57cf81dfaebfaba57e95dfa84db85f
+size 501599488

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": true,
+    "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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}