BlinkDL/RWKV-LM

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

⭐ 14393 | 🍴 990

thtrieu/darkflow

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

⭐ 6154 | 🍴 2044

giltene/wrk2

A constant throughput, correct latency recording variant of wrk

⭐ 4553 | 🍴 419

Charmve/Surface-Defect-Detection

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

⭐ 3953 | 🍴 596