Cola Chan's starred repositories
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.
DeepSpeedExamples
Example models using DeepSpeed
alignment-handbook
Robust recipes to align language models with human and AI preferences
awesome-RLHF
A curated list of reinforcement learning with human feedback resources (continually updated)
llm_interview_note
主要记录大语言大模型(LLMs) 算法(应用)工程师相关的知识及面试题
Awesome-LLM-KG
Awesome papers about unifying LLMs and KGs
llm-hallucination-survey
Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"
TruthfulQA
TruthfulQA: Measuring How Models Imitate Human Falsehoods
Multi-view-Consistency-for-MWP
EMNLP22: Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
finetuned-qlora-falcon7b-medical
Finetuning of Falcon-7B LLM using QLoRA on Mental Health Conversational Dataset
Emotional-Support-Conversation
Data and codes for ACL 2021 paper: Towards Emotional Support Dialog Systems
mPLUG-HalOwl
mPLUG-HalOwl: Multimodal Hallucination Evaluation and Mitigating
llm-uncertainty
code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"
Synthetic-Persona-Chat
The Synthetic-Persona-Chat dataset is a synthetically generated persona-based dialogue dataset. It extends the original Persona-Chat dataset.
Self-Verification
We have released the code and demo program required for LLM with self-verification
ChatProtect
This is the code for the paper "Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation".