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
+crag_model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -12,8 +12,8 @@ tags:
 - dual-encoder
 - clinical-nlp
 datasets:
+- ade_corpus_v2
 - bigbio/mimicause
-- ade-benchmark-corpus/ade_corpus_v2
 metrics:
 - f1
 - precision
@@ -234,6 +234,36 @@ The model was trained on a combination of:
 | Loss Function | InfoNCE (τ=0.07) | Focal (γ=2.0, α=0.75) |
 | Hard Negatives | 50% | - |
 
+## Experiment Tracking
+
+- **WandB Run**: [68d4wq4u](https://wandb.ai/chrisvoncsefalvay/crag-experiments/runs/68d4wq4u)
+- **Dataset Artifacts**: [HuggingFace Dataset](https://huggingface.co/datasets/chrisvoncsefalvay/crag-experiment-artifacts)
+
+## ONNX Export
+
+An ONNX export is provided for deployment flexibility:
+
+```python
+import onnxruntime as ort
+from huggingface_hub import hf_hub_download
+
+# Download ONNX model
+onnx_path = hf_hub_download(
+    repo_id="chrisvoncsefalvay/CRAG-dual-encoder-mimicause",
+    filename="crag_model.onnx"
+)
+
+# Create inference session
+session = ort.InferenceSession(onnx_path)
+
+# Run inference (see pytorch example for input preparation)
+outputs = session.run(None, {
+    "drug_input_ids": drug_ids,
+    "drug_attention_mask": drug_mask,
+    "adr_input_ids": adr_ids,
+    "adr_attention_mask": adr_mask
+})
+```
 
 ## Limitations
 
@@ -258,4 +288,4 @@ If you use this model, please cite:
 
 ## License
 
-Apache 2.0
+Apache 2.0

crag_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa84ab29b3086f4c2de91f8d912f4a0e01aa446289e1e1faa406ae72cbb35deb
+size 3041204

crag_model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e60f287de4c052fe3efe293305d5236079b6b6439c9fd038287db239b17487
+size 950510592