-
Card: v0.5.2 benchmarks; BGL operator-log regression named
-
OpenJevX v0.5.2: model folder (8-bit ONNX, config, tokenizer), fine-tune checkpoint, card
-
Card: v0.5.1 server latency (ORT 1.29); model unchanged
-
OpenJevX v0.5.0: model folder (config.json temperatures, tokenizer.json), clean-gate card, Python helper reads config.json
-
OpenJevX v0.5.0: 8-bit ONNX (CPU-first) and fine-tune checkpoint
-
Model card: example output rounded
-
Model card: run it in a container (recommended) or from Python; links
-
Add openjevx.py: run the model from Python with the same answers as the server
-
Checksums for v0.4.0 files
-
OpenJevX v0.4.0: fine-tuned model, 8-bit and fp32 ONNX
-
Publish OpenJevX RLCD checkpoint and ONNX export
-
initial commit
