TeleOCR parses scans, PDFs and photos, supporting complex layouts, tables, formulas and charts. OmniDocBench V1.6 (96.87) and Wild-OmniDocBenc(88.53).
AI & ML interests
XingChen-AGI is the open-source organization, dedicated to building agent-era large language models. Our flagship Xing4.0-29B-A4B is a 29B MoE model with only 4B activated parameters, natively supporting 256K context (extensible to 512K). With 4-bit quantization, it runs on a single consumer GPU (~15GB VRAM) and scores 93.52 on SuperCLUE Agent benchmark.
Recent Activity
models 4
XingChen-AGI/TeleOCR
Image-Text-to-Text • 1B • Updated • 35.4k • 1.27k
XingChen-AGI/Xing4.0-29B-A4B-GGUF
Text Generation • 31B • Updated • 20.5k • 155
XingChen-AGI/Xing4.0-29B-A4B-FP8
Text Generation • 31B • Updated • 965 • 122
XingChen-AGI/Xing4.0-29B-A4B
Text Generation • 31B • Updated • 50k • 1.83k
datasets 0
None public yet