Hugging Face's logo

Spaces:
build-small-hackathon
/
unstuck
Running on Zero

App Files Community
unstuck / src

Commit History

fix(recall): default embed model to Qwen3-Embedding-8B
52b7250
Running
verified

art87able commited on

deploy: multi-backend (minicpm/nemotron/finetuned) + 3-tier ZeroGPU->serverless->local-finetune fallback; finetune pipeline
fe7f8fd

art87able commited on

feat: similar-task recall via Nebius embeddings (keyless; recall degrades off without NEBIUS_API_KEY)
79e91df
verified

art87able commited on

deploy: offgrid on-device backend
f852d34
verified

art87able commited on

Upload folder using huggingface_hub
ce5b6f9
verified

art87able commited on

Upload folder using huggingface_hub
7a754d7
verified

art87able commited on

Upload src/unstuck/store.py with huggingface_hub
5338711
verified

art87able commited on

Upload src/unstuck/prompts.py with huggingface_hub
81858de
verified

art87able commited on

Upload src/unstuck/store.py with huggingface_hub
f9fc575
verified

art87able commited on

Upload src/unstuck/prompts.py with huggingface_hub
e75a19e
verified

art87able commited on

fix: thread-safe SQLite store
a98f11a
verified

art87able commited on

fix: unpack BatchEncoding into model.generate
3080b01
verified

art87able commited on

fix(zerogpu): load model with .to(cuda) instead of device_map
012de31
verified

art87able commited on

Deploy Unstuck (Codex-built) — initial code
2f62bd4
verified

art87able commited on