Minimize ZeroGPU utilization time by cutting out SentenceTransformer overhead 303669c Running colonelwatch commited on 20 days ago
Pull in index from new repository, due to LFS size limits on HF Spaces 92365df colonelwatch commited on 27 days ago
Add a better reference to the model and the date of the dataset to the description b37a6fe colonelwatch commited on 27 days ago
Handle new params.json format, including truncation and normalization 4751a57 colonelwatch commited on Dec 14, 2024
Run model on GPU and add fp16 and trust_remote_code options 22ed20d colonelwatch commited on Nov 17, 2024
Resolve TODO as won't do and use correct float type for env var 8b17b49 colonelwatch commited on Nov 17, 2024
Shuffle around contents of execute_request, format_response, and search ddc3a5a colonelwatch commited on Nov 17, 2024