Pinned Repositories
AI_analysis
analysis of problems of AI and Math
cuda_learning
learning how CUDA works
langchain-llama
Reinforcement learning based pricing for demand response
LLMTrainer
A comparison of pretraining framework for LLM
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
Qtrading
llm.c
LLM training in simple, raw C/CUDA
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Qwen1.5
Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.
ifromeast's Repositories
ifromeast/cuda_learning
learning how CUDA works
ifromeast/Qtrading
ifromeast/LLMTrainer
A comparison of pretraining framework for LLM
ifromeast/langchain-llama
Reinforcement learning based pricing for demand response
ifromeast/AI_analysis
analysis of problems of AI and Math
ifromeast/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)