Hugging Face's logo

Spaces:
LLDDWW
/
MedCard
Sleeping

App Files Community
MedCard

Commit History

perf: preload models at startup for faster inference
ab48ca2

LLDDWW Claude commited on

fix: strip whitespace from HF_TOKEN
115fae5

LLDDWW Claude commited on

chore: upgrade to MedGemma-4B-IT for medical analysis
f89c606

LLDDWW Claude commited on

chore: upgrade to MedGemma-4B-IT for medical analysis
7d833fa

LLDDWW Claude commited on

feat: use Gemma-2-2B for medical analysis
d5aff0d

LLDDWW Claude commited on

feat: add medication analysis with easy explanations
0e6a905

LLDDWW Claude commited on

chore: upgrade to Qwen2.5-VL-7B-Instruct
8a7e01c

LLDDWW Claude commited on

fix: use correct Qwen2_5_VL class for Qwen2.5-VL model
c5fa8ab

LLDDWW Claude commited on

chore: switch to Qwen2.5-VL-3B-Instruct for OCR
664b899

LLDDWW Claude commited on

feat: upgrade to Qwen2-VL-2B for state-of-the-art OCR
28a7334

LLDDWW Claude commited on

fix: move EasyOCR initialization inside GPU decorator
0ffc67e

LLDDWW Claude commited on

feat: switch from PaddleOCR to EasyOCR
33831f7

LLDDWW Claude commited on

fix: update PaddleOCR initialization parameters
70f28f9

LLDDWW Claude commited on

feat: switch to PaddleOCR for better Korean text recognition
f16cb1a

LLDDWW Claude commited on

refactor: simplify to OCR-only output
39446f7

LLDDWW Claude commited on

chore: switch to Korean-optimized TrOCR model
7138a91

LLDDWW Claude commited on

fix: match input dtype to model dtype for TrOCR
c74ab95

LLDDWW Claude commited on

fix: remove torch_dtype to fix TrOCR dtype mismatch
e4a5da6

LLDDWW Claude commited on

chore: switch OCR model to TrOCR
6a2327c

LLDDWW Claude commited on

sdfdsfads23333
e94e117

LLDDWW commited on

sdfdsfads23333
92bb45b

LLDDWW commited on

sdfdsfads2333
64c57fb

LLDDWW commited on

sdfdsfads233
52bda02

LLDDWW commited on

refactor: simplify to medication name extractor only
7ce0e26

LLDDWW Claude commited on

sdfdsfads23
ea6e0a5

LLDDWW commited on

sdfdsfadsㄴ
e5ef627

LLDDWW commited on

sdfdsfads
bfe2214

LLDDWW commited on

fix: resolve 401 error by using public Qwen2-VL-7B model with ultra quality optimizations
24e39c0

LLDDWW Claude commited on

sdf
736677f

LLDDWW commited on

feat: upgrade to 72B model with 8-bit quantization for maximum quality
e5f80e3

LLDDWW Claude commited on

fix: change to VL-7B for ZeroGPU compatibility
84e5d9f

LLDDWW commited on

feat: complete redesign with single VL-32B model and modern UI
98b216f

LLDDWW Claude commited on

feat: add real-time web search for drug verification
3cec557

LLDDWW commited on

feat: ultra-quality improvement for production-ready app
8020bc3

LLDDWW Claude commited on

feat: add professional drug information system
ad98685

LLDDWW Claude commited on

fix: change image model to SDXL (FLUX access restricted)
88cbfb6

LLDDWW commited on

feat: optimize performance and improve UX (Phase 1)
5e231af

LLDDWW Claude commited on

feat: upgrade models and improve quality
8a13800

LLDDWW Claude commited on

123453
31407b3

LLDDWW commited on

feat: add qwen vl narratives and cartoon generation
e53f54d

LLDDWW commited on

12345
dbf7d32

LLDDWW commited on

1234
45e929d

LLDDWW commited on

chore: mark vision analysis for gpu execution
69a39af

LLDDWW commited on

123
e8a6e3f

LLDDWW commited on

update requirements txt
1e3eef4

LLDDWW commited on

refactor: switch to qwen vl multimodal analysis
459e392

LLDDWW commited on

fix: tolerate non-numeric paddleocr boxes
b387d82

LLDDWW commited on

fix: guard paddleocr confidence parsing
8e8ea94

LLDDWW commited on

fix: handle paddleocr output variants
7cb5d13

LLDDWW commited on

fix: update paddleocr call signature
11e0add

LLDDWW commited on