ftmu's repositories
ContrastiveNarratives
Generating Contrastive Narratives Using the Brownian Bridge Process for Narrative Coherence Learning
fucking-algorithm
手把手撕LeetCode题目,扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.
alpaca-lora
Instruct-tune LLaMA on consumer hardware
build_MiniLLM_from_scratch
从0到1构建一个MiniLLM
CausalityEventExtraction
Causality event extraction demo project including casual patterns and experiment on large scale corpus. 基于因果关系知识库的因果事件图谱实验项目,本项目罗列了因果显式表达的几种模式,基于这种模式和大规模语料,再经过融合等操作,可形成因果事件图谱。
Chain-of-ThoughtsPapers
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
ChatReviewer
ChatReviewer: use ChatGPT to review papers; ChatResponse: use ChatGPT to respond to reviewers.
CREST
A Causal Relation Schema for Text
DenoisingDiffusionProbabilityModel-ddpm-
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
DisExtract
The library that uses dependency parsing to preprocess text to train DisSent model
EventPredictBasedOnEG
future event predict demo based on causal event graph that covers the full industries that can predict the benefits or bad effects in accordance with the event given by the user, 基于因果事理图谱的事件预测。
EventCommonSenseKnowledge_dissertation
All event relational knowledge extracted by previous papers (in Ph.D. dissertation). This knowledge include subevent, temporal, and causal relations between events.
generative_agents
Generative Agents: Interactive Simulacra of Human Behavior
Glasgow-NLP
This is a repository designed to be my portable workstation. I can use it on a CPU or GPU machine and is meant for development and training. It contains docker files for environment setup and links to other repositories that can be downloaded inside.
mufeiteng.github.io
Homepage of Mu Feiteng
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
PRML
PRML algorithms implemented in Python
pulp
A python Linear Programming API
RWKV-LM
RWKV is an 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.
trader
交易模块