Update modeling_nemotron_h.py (#36)

Update config.json (#35)

Update README.md

Fixing nested JSON args parsing for tool-calls in streaming (#32)

Updating streaming tool-call parser to return ChoiceDeltaToolCall (#31)

Upload streaming tool call parser python file for vLLM (#30)

Update modeling_nemotron_h.py

Update README.md

Update README.md

Update README.md

Update README.md

Use remaining_tokens for max_tokens in vLLM token budget demo

Update README.md

Update README.md

Update README.md (#13)

Fix model_max_length (#11)

Upload modeling_nemotron_h.py (#10)

Update README.md

Update config.json

Update README.md

Updating evaluation details for RULER (reasoning off) (#6)

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Minor fixes in example code snippets and chat template description (#2)

Update README.md

Upload accuracy_chart.png

Update README.md

Upload accuracy_chart.png

Update README.md

Update README.md

Update README.md

Upload acc-vs-budget.png

Upload 5 files

Update chat template for adding sys header even when no sys message, and allowing assistant response pre-fixing (#1)

Upload nemotron_toolcall_parser_no_streaming.py

Upload folder using huggingface_hub

initial commit