Commit History

Make image upload guidance wrapper-independent
7cfef5a

Abid Ali Awan Codex commited on

Handle invalid image generation as upload guidance
4149e50

Abid Ali Awan Codex commited on

Add local CUDA deployment and reject non-notice images
8ccb3e9

Abid Ali Awan Codex commited on

Add notice image guidance and update runtime docs
edecb11

Abid Ali Awan Codex commited on

Simplify status badge text
fb8ab7d

Abid Ali Awan Codex commited on

Remove logging from app modules
ed9b3cc

Abid Ali Awan Codex commited on

Add fallback values for empty red_flags and safe_next_steps
23aaddf

Abid Ali Awan Codex commited on

Preload Nemotron-Parse model at startup
e289ef1

Abid Ali Awan Codex commited on

Log detailed error when Nemotron-Parse fails to load
b5fbf31

Abid Ali Awan Codex commited on

Replace Nemotron OCR v2 with Nemotron-Parse-v1.2
a03a0fe

Abid Ali Awan Codex commited on

Catch ZeroGPU quota errors and reduce GPU duration to 45s
429a368

Abid Ali Awan Codex commited on

Add logging for model response diagnostics on Spaces
c6454a8

Abid Ali Awan Codex commited on

Handle malformed and Urdu OCR responses
b9df8c6

kingabzpro Codex commited on

Remove temporary runtime probes
26a1970

kingabzpro Codex commited on

Add temporary OCR runtime probe
e22d004

kingabzpro Codex commited on

Simplify MiniCPM JSON instructions
20440cf

kingabzpro Codex commited on

Create tensor chat inputs for MiniCPM
9d32812

kingabzpro Codex commited on

Trace Space loader exception chain
e7ac81c

kingabzpro Codex commited on

Report chained Space loader error
1f07499

kingabzpro Codex commited on

Add temporary Space runtime probe
24a92bb

kingabzpro Codex commited on

Use MiniCPM Transformers generation flow
ede31c9

kingabzpro Codex commited on

Stop GGUF prefetch on ZeroGPU
520fbe6

kingabzpro Codex commited on

Separate Space and local model runtimes
cc3c1a2

kingabzpro Codex commited on

Use CPU llama.cpp on ZeroGPU Space
f6bf978

kingabzpro Codex commited on

Initialize CUDA before llama.cpp
cd380a1

kingabzpro Codex commited on

Load CUDA runtime before local models
9e548e3

kingabzpro Codex commited on

Return bounded worker diagnostic
09a1d4c

kingabzpro Codex commited on

Capture MiniCPM response shape
b5c744d

kingabzpro Codex commited on

Finalize ZeroGPU runtime handling
d99006b

Kingabzpro Codex commited on

Capture wrapped ZeroGPU diagnostic
d381615

Abid Ali Awan OpenAI Codex commited on

Expose temporary ZeroGPU diagnostic
c7d45fc

Abid Ali Awan OpenAI Codex commited on

Add temporary model runtime diagnostic
77f430e

Abid Ali Awan OpenAI Codex commited on

Fix NoticeCheck runtime and final styling
67a2445

Abid Ali Awan OpenAI Codex commited on

Constrain MiniCPM output to assessment JSON
551145e

Abid Ali Awan OpenAI Codex commited on

Refactor and rebrand app as NoticeCheck
6cf9641

Abid Ali Awan OpenAI Codex commited on