GenericAgent
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
- 14k
- Python
- MIT
- 1 d ago
lsdefine
Built from lsdefine's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
A very simple GRPO implement for reproducing r1-like LLM thinking.
A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need
Low ReSource Reinforcement Learning with CPU Offloading Training Support
The API utils for querying CN-DBpedia & CN-Probase, the biggest Chinese knowledge bases
Deploy DeepSeek-V4.1 (dsv4.1) on Ascend 910B / 910B3 (NPU): a hardware-specialized LLM inference engine with W4A8, DSpark speculative decoding, 128K+ context and 8,700+ tok/s prefill. Also supports NVIDIA A100/A800. 昇腾910B 部署 DeepSeek-V4.1-Flash。
Pretrain own bert / roberta model with wwm-mlm and modified tokenizer (both chinese and english).