| title: AGILLM 4.3 ZeroGPU GUI | |
| emoji: ⚡ | |
| colorFrom: indigo | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| python_version: 3.10.13 | |
| app_file: app.py | |
| pinned: false | |
| startup_duration_timeout: 1h | |
| models: | |
| - OpenTransformer/AGILLM-4.3 | |
| tags: | |
| - text-generation | |
| - pytorch | |
| - gradio | |
| - zerogpu | |
| - agillm | |
| # AGILLM 4.3 ZeroGPU GUI | |
| Gradio Space version of the AGILLM 4.3 local inference GUI for Hugging Face ZeroGPU. | |
| This Space uses the same preferred `pretrain_delta_step00363424_20260703T1105Z.pt` checkpoint from `OpenTransformer/AGILLM-4.3`. | |
| Inference runs inside a `spaces.GPU` call and supports Streaming vs Full result output. ZeroGPU is quota-limited, so shorter Max values are friendlier to the queue. | |