Jiaxin Zhang's repositories
Awesome-LLM-RAG
Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models
Awesome-LLM-Fine-Tuning-Alignment
LLM fine-tuning
awesome-production-machine-learning
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
prompt2model
prompt2model - Generate Deployable Models from Natural Language Instructions
promptbase
All things prompt engineering
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
axolotl
Go ahead and axolotl questions
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Knowledge_Card
Code for "Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models", ICLR 2024 Oral.
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
llm-autoeval
Automatically evaluate your LLMs in Google Colab
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
llm-datasets
High-quality datasets, tools, and concepts for LLM fine-tuning.
math-evaluation-harness
A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨
MedRAG
Code for the MedRAG toolkit
MIRAGE
Official repository of the MIRAGE benchmark
orpo
Official repository for ORPO
RAG-Retrieval
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder
rep-to-string-counterfactuals
The repo of the paper: "Converting Representational Counterfactuals to Natural Language"
Retrieval_Head
open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality
rho1
Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
SPUQ
SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models
StructLM
Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding"
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
Yi
A series of large language models trained from scratch by developers @01-ai