Spaces:

Duplicated from SEE7/Astheral

SEE7
/

AstheralPlus

Paused

App Files Files Community

5.88 MB

Ctrl+K

Ctrl+K

1 contributor

History: 31 commits

SEE7's picture

Forward project context through a dedicated Gradio input instead of filtered chat history

d2287b7 verified 1 day ago

llama-ui
Keep complete chat URLs and reset project context for new conversations 1 day ago
tests
Record completed public Space integration tests 1 day ago
.gitattributes

1.52 kB
initial commit 2 days ago
LICENSE

11.4 kB
Implement 20.9B native reasoning inference and persistent project workspaces 1 day ago
LLAMA_UI_LICENSE

1.08 kB
Install real llama-ui with streaming Astheral ZeroGPU adapter and existing quota guard 2 days ago
README.md

1.3 kB
Implement 20.9B native reasoning inference and persistent project workspaces 1 day ago
app.py

4.79 kB
Forward project context through a dedicated Gradio input instead of filtered chat history 1 day ago
gguf_models.py

4.32 kB
Add private GGUF upload, model selection and quota-guarded CUDA inference 2 days ago
gguf_runtime.py

1.85 kB
Allow 4096-token replies and 110-second generation with 180-second quota reserve 2 days ago
llama_ui.py

11.1 kB
Forward project context through a dedicated Gradio input instead of filtered chat history 1 day ago
quota_guard.py

622 Bytes
Implement 20.9B native reasoning inference and persistent project workspaces 1 day ago
requirements.txt

134 Bytes
Pin GPT-OSS MXFP4 compatible kernel runtime 1 day ago