db10c98c6ea4686e3b78777e9e913487e765d649
- Removed all OpenAI/Anthropic/Abbott/AbbVie/J&J references from 11 pages - Removed all internal IPs (88.198.4.195, 89.167.40.150) from placeholders - Removed hardcoded API key 'weval-playground-2026' from gpu-inference.html - Aligned GPU model names: qwen2.5:3b, phi3:mini, gemma2:2b (matches S202) - Replaced all Anthropic API calls with /api/content/generate.php proxy - Genericized MedReach country counts (no internal numbers) - Removed expansion dates (Q3/Q4 2026) and source names (EgyDoctors, DoktorTakvimi, SCFHS, Doctolib) - Replaced internal numbers (646, 604, 527, 1783, CX3, DoubleM) with generics - Internationalized all footers (Casablanca,Maroc -> International) - Replaced PMTA references in product catalogs with generic terms - Fixed Roadmap -> Plan de deploiement in products-index.html Co-authored-by: Yacineutt <Yacineutt@users.noreply.github.com>
WEVADS GPU Server
- IP: 88.198.4.195
- GPU: NVIDIA RTX 4000 SFF Ada (20GB vRAM)
- RAM: 62GB DDR4
- Disk: 1.7TB NVMe
- Ollama: localhost:11434
- Models: deepseek-r1:8b, deepseek-r1:32b, llama3.1:8b
Description
Languages
HTML
93.1%
Shell
4.3%
PHP
2.6%