cms42's repos on GitHub
Python · 2 watchers
Megatron-LM
Ongoing research training transformer models at scale
0 watchers
DeepEP
DeepEP: an efficient expert-parallel communication library
JavaScript · 0 watchers
hustoj
Popular Open Source Online Judge based on PHP/C++/MySQL/Linux for ACM/ICPC and NOIP training, with easy installation. 开源OJ系统
0 watchers
mlx-qwen3-asr
Qwen3-ASR speech recognition on Apple Silicon via MLX
0 watchers
MOSS-Audio-Tokenizer
MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.
0 watchers
MOSS-TTS
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.
PHP · 0 watchers
nexusphp
A private tracker application base on NexusPHP
Python · 0 watchers
RWKV-LM-LoRA
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
0 watchers
treehole_next
Next generation of Open Tree Hole written in go