plural for Manifests

Align with OFPBadWord pattern: FastAPI app, clean routes, no ZeroGPU

Fix OFP routing: use Starlette middleware instead of include_router

Optimize Qwen3 for fast social chat: disable thinking mode, cap tokens

Fix routing: change from /api/ to /ofp-api/ prefix (Gradio reserves /api/)

Fix OFP routing: add /api/ prefix to bypass Gradio SvelteKit catch-all

chenage for api/ofp

app.py changes

er gpu changes

added smaller qwne model

decoration try for zero GPU

decoratort issue

try add gpu decorator

fix

fix

GPU enabled

ui and error fix

be fix

qwen 3 through transformers

qwen 3

UPdate your project to use Qwen3-4B-Instruct-2507 and remove all other model references

docs: add comprehensive final deployment report for Talker agent

# Talker - OFP Chat Agent Configuration

error fix

i

Update Mistral model to v0.3

fast api enabled

Fix Gradio ChatInterface parameters

Fix Gradio ChatInterface parameters

Fix Gradio ChatInterface parameters

modified short description

configuration header added

initial commit

initial commit