doitmagic/ wedlm-7b-base

60 1 month ago

Tencent WeDLM-7B-Base converted to GGUF (Q4_K_M). A text-diffusion model based on Qwen2.5 architecture, optimized for efficient parallel decoding.

1 model

wedlm-7b-base:latest
48ef8603a470 • 4.7GB • 16K context window •
Text input • 1 month ago