Sathvik A R

Sathvik0101

·

AI & ML interests

None yet

Organizations

New activity in Sathvik0101/Avyaya-voice-intelligence 3 months ago

Upload folder using huggingface_hub

#29 opened 3 months ago by

feat: strict-latency deadline guard, grammar-constrained GGUF decoding, hardened guardrails

#28 opened 3 months ago by

fix: hard 30s generation timeout and slow-first-attempt recovery guard

#27 opened 3 months ago by

feat: resident extractive fast tier, bounded generation recovery, fast-tier-only mode

#25 opened 3 months ago by

fix: drop obsolete ambient reset rule for fixed background

#26 opened 3 months ago by

feat: pre-download extractive fast-tier QA model at Space boot

#24 opened 3 months ago by

fix: generate multilingual answers instead of extracts

#23 opened 3 months ago by

fix: initialize Space UI interactions

#22 opened 3 months ago by

fix: export Qwen model for Space startup

#21 opened 3 months ago by

Fix multilingual retrieval and Qwen fallback

#20 opened 3 months ago by

Rebase retrieval latency optimization onto latest Space

#18 opened 3 months ago by

Fix selected output language end to end

#17 opened 3 months ago by

Optimize retrieval quality and answer latency

#12 opened 3 months ago by

Make the UI visibly clearer and more useful

#13 opened 3 months ago by

Activate ZeroGPU for Qwen generation

#10 opened 3 months ago by

Improve answer UX and provenance transparency

#11 opened 3 months ago by

Honor selected answer language

#9 opened 3 months ago by

Remove slow GGUF JSON grammar and shrink multilingual prompt

#8 opened 3 months ago by

Use Blackwell cu130 Q4 runtime and short multilingual generation path

#7 opened 3 months ago by

Fallback to CPU llama.cpp when ZeroGPU CUDA GGUF kernels fail

#6 opened 3 months ago by