Upload folder using huggingface_hub

README.md

@@ -0,0 +1,48 @@
+# SWE-Pruner ONNX (code-pruner)
+
+ONNX-converted version of [ayanami-kitasan/code-pruner](https://huggingface.co/ayanami-kitasan/code-pruner) for efficient CPU inference.
+
+## Source
+
+- **Original Model**: [ayanami-kitasan/code-pruner](https://huggingface.co/ayanami-kitasan/code-pruner) (safetensors)
+- **Training Code**: [Ayanami1314/swe-pruner](https://github.com/Ayanami1314/swe-pruner)
+
+## Architecture
+
+- **Backbone**: Qwen/Qwen3-Reranker-0.6B (28 layers, hidden=1024)
+- **Multi-layer Fusion**: Early (layer 7) + Middle (layer 14) + Final (layer 28) → fused_hidden=3072
+- **Fusion**: 1-layer MultiheadAttention (8 heads) + LayerNorm
+- **Compression Head**: CRF-style (LayerNorm → Linear(3072,256) → GELU → Linear(256,2))
+- **Output**: `token_scores` — sigmoid scores per token (0-1, higher = keep)
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `model.onnx` | Quantized ONNX model (uint8, ~607MB) |
+| `vocab.json` | BPE vocabulary (Qwen3 tokenizer) |
+| `merges.txt` | BPE merge rules |
+| `metadata.json` | Model metadata (token IDs, dimensions) |
+| `crf_params.npz` | CRF transition parameters (optional, for Viterbi decoding) |
+
+## Usage
+
+```python
+import onnxruntime as ort
+import numpy as np
+
+sess = ort.InferenceSession("model.onnx")
+input_ids = np.array([[...]], dtype=np.int64)      # [1, seq_len]
+attention_mask = np.array([[...]], dtype=np.int64)  # [1, seq_len]
+
+scores = sess.run(None, {"input_ids": input_ids, "attention_mask": attention_mask})[0]
+# scores: [1, seq_len] float32, 0-1 range, higher = keep
+```
+
+## Conversion Details
+
+- Exported with PyTorch 2.8 + transformers 4.57
+- Opset version: 14
+- Dynamic axes: batch and seq_len
+- Quantized: dynamic uint8 quantization
+- Causal mask patched for ONNX trace compatibility

crf_params.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d8a7c8c5b25418750e99d59497b81eb758fc9a6ca54af631d9f9b384bfb0bc
+size 836

metadata.json

@@ -0,0 +1,10 @@
+{
+  "model_type": "swepruner",
+  "backbone": "Qwen/Qwen3-Reranker-0.6B",
+  "hidden_size": 1024,
+  "fused_hidden_size": 3072,
+  "compression_head_type": "crf",
+  "token_yes_id": 9693,
+  "token_no_id": 2152,
+  "output": "token_scores (sigmoid, 0-1, higher=keep)"
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f81b0977a8e96350271637b825a7a99b5be74d82b528977f9a034b11752734f
+size 636820889