Spaces:

bottlecapai
/

ThinkingCap-vs-Qwen3.8-27B

Running

App Files Files Community

ThinkingCap-vs-Qwen3.8-27B

365 kB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

oplatek's picture

Precomputed examples: Replay button streaming at live decoding speed

18933de verified about 2 months ago

.gitattributes

1.52 kB
initial commit about 2 months ago
README.md

853 Bytes
CPU orchestrator over two bf16 ZeroGPU backends about 2 months ago
app.py

17.1 kB
Precomputed examples: Replay button streaming at live decoding speed about 2 months ago
chain.py

1.83 kB
Time reasoning as decode time from the first new token about 2 months ago
chat_utils.py

9.46 kB
Per-model GPU-measured reasoning time about 2 months ago
examples.json

323 kB
Add precomputed multi-seed examples tab; longer first step for signed-in visitors about 2 months ago
examples.py

5.6 kB
Precomputed examples: Replay button streaming at live decoding speed about 2 months ago
generation.py

4.13 kB
CPU orchestrator over two bf16 ZeroGPU backends about 2 months ago
requirements.txt

87 Bytes
CPU orchestrator over two bf16 ZeroGPU backends about 2 months ago
ui.py

1.01 kB
Add precomputed multi-seed examples tab; longer first step for signed-in visitors about 2 months ago