Sathvik A R

Sathvik0101

·

AI & ML interests

None yet

Recent Activity

updated a Space about 1 month ago

Sathvik0101/Avyaya-voice-intelligence

new activity about 1 month ago

Sathvik0101/Avyaya-voice-intelligence:Upload folder using huggingface_hub

new activity about 1 month ago

Sathvik0101/Avyaya-voice-intelligence:feat: strict-latency deadline guard, grammar-constrained GGUF decoding, hardened guardrails

View all activity

Organizations

New activity in Sathvik0101/Avyaya-voice-intelligence about 1 month ago

Upload folder using huggingface_hub

#29 opened about 1 month ago by

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

#28 opened about 1 month ago by

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

#27 opened about 1 month ago by

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

#25 opened about 1 month ago by

fix: drop obsolete ambient reset rule for fixed background

#26 opened about 1 month ago by

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

#24 opened about 1 month ago by

fix: generate multilingual answers instead of extracts

#23 opened about 1 month ago by

fix: initialize Space UI interactions

#22 opened about 1 month ago by

fix: export Qwen model for Space startup

#21 opened about 1 month ago by

Fix multilingual retrieval and Qwen fallback

#20 opened about 1 month ago by

Rebase retrieval latency optimization onto latest Space

#18 opened about 1 month ago by

Fix selected output language end to end

#17 opened about 1 month ago by

Optimize retrieval quality and answer latency

#12 opened about 1 month ago by

Make the UI visibly clearer and more useful

#13 opened about 1 month ago by

Activate ZeroGPU for Qwen generation

#10 opened about 1 month ago by

Improve answer UX and provenance transparency

#11 opened about 1 month ago by

Honor selected answer language

#9 opened about 1 month ago by

Remove slow GGUF JSON grammar and shrink multilingual prompt

#8 opened about 1 month ago by

Use Blackwell cu130 Q4 runtime and short multilingual generation path

#7 opened about 1 month ago by

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

#6 opened about 1 month ago by