Upload qora.exe with huggingface_hub

Upload README.md with huggingface_hub

Update README.md

Remove source files (uploaded by mistake)

Update exe: loop detection, think budget, greedy fix, concise responses

System prompt: concise responses after thinking

Add --think-budget CLI arg

GPU inference: consistent greedy/think fixes

Fix greedy/think mode: loop detection, think budget, EOS blocking

Update README.md

Update README.md

Rebuild qora.exe: 0 warnings, GPU+CPU

Update README.md

Remove source files - only distributable files belong here

Update qora.exe: remove safetensors fallback, GPU+CPU build

Remove safetensors fallback: clean main/gemv/lib/Cargo.toml

Remove safetensors fallback, update CLI args and defaults

Update README.md

Update qora.exe: GPU+CPU build with Vulkan auto-detect (~37 MB)

Update README: add GPU acceleration support (Vulkan, ~4.8x speedup)

Upload folder using huggingface_hub

Update config.json

Upload qora.exe with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload model.qora with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload qora.exe with huggingface_hub

Upload config.json with huggingface_hub

Upload README.md with huggingface_hub

initial commit