Spaces:
Running on Zero
Running on Zero
Commit History
-
feat: increase default max_new_tokens to 384 (max 1024) and enforce sentence completion Running
3ace22d -
feat: organize catalog by vendor/size and activate gemma4-e4b and kanana-2-3b
ed0b0be -
style: update markdown heading for summarizers output
203c07b -
feat: prioritize Side-by-Side SLM tab and generalize input parser methods
e78f1af -
feat: separate SLM execution trigger and add automatic zero-failure CPU fallback
f06c5d9 -
refactor: consolidate SLM summary executions into single @spaces.GPU call to prevent quota throttle
af7ed1f -
feat: restore ZeroGPU CUDA execution mode with grace fallback messaging
e3d0009 -
feat: add ZeroGPU platform probe and route lightweight SLMs directly to CPU
461b5d3 -
feat: integrate ultra-lightweight hybrid SLM models for instant CPU/GPU benchmarking
af52cc7 -
fix: guard against CPU fallback during ZeroGPU allocation drops and reduce default tokens
afbaaaf -
fix: restore missing parenthesis in AutoModelForCausalLM call
3bbbf5d -
fix: eliminate module-level cuda calls and align with ZeroGPU default python runtime
e47379e -
fix: attach @spaces.GPU directly to Gradio event handlers and chain execution
1b8b3a1 -
fix: resolve sumy ObjectDocumentModel and ZeroGPU CUDA wrapper initialization
9cc8c20 -
fix: remove invalid ssr argument from demo.launch
32312b0 -
fix: disable api_name, ssr, show_api and remove complex type hints to prevent Gradio 5.20 get_api_info crash
5f03cb1 -
fix: isolate error handling, fix chat history streaming, and switch default active to native bfloat16 models
3e6e80a -
chore: ignore .env
2de5589 -
feat: implement Frontier SLM Comparison & Text Summarizers
97d08f3