Pinned Repositories
json2binidx_tool
RWKV-infctx-trainer-LoRA
RWKV v5, v6 infctx LoRA trainer ,Cuda and Rocm supported, for training arbitary context sizes, to 10k and beyond!
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.
tf-idf-keyword
Keyword extraction based on TF-IDF on specific corpus. 基于特定语料库的TF-IDF的中文关键词提取
RWKV-infctx-trainer-LoRA
RWKV v5, v6 infctx LoRA trainer with 4bit quantization,Cuda and Rocm supported, for training arbitary context sizes, to 10k and beyond!
ChinesePainting's Repositories
ChinesePainting/json2binidx_tool
ChinesePainting/RWKV-infctx-trainer-LoRA
RWKV v5, v6 infctx LoRA trainer ,Cuda and Rocm supported, for training arbitary context sizes, to 10k and beyond!
ChinesePainting/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.
ChinesePainting/tf-idf-keyword
Keyword extraction based on TF-IDF on specific corpus. 基于特定语料库的TF-IDF的中文关键词提取