jimxionggm Goto Github PK

agentbench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

benchmarkingzeroshot

blink

Entity Linker solution

bmtools

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

chain-of-thought-hub

Benchmarking LLM reasoning performance w. chain-of-thought prompting

crawlpaper4nlp

dail-sql

A efficient and effective few-shot NL2SQL method on GPT-4.

deepctr-torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

deepspeedexamples

Example models using DeepSpeed

dianyingtt_scrapy

基于scrapy框架的电影天堂网站爬取器

dstc2_baselines

dstc8-schema-guided-dialogue

The Schema-Guided Dialogue Dataset

dts-sql

This repository contains all the code for the DTS-SQL paper

fastchat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

few-shot-nl2sql-with-prompting

firefly

Firefly: 大模型训练工具，支持训练Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

glad

Global-Locally Self-Attentive Dialogue State Tracker

interactive-kbqa

A KBQA solution framework based on the agent-environment paradigm in the era of LLMs.

jimxionggm.github.io

kb-binder

Few-shot In-context Learning for Knowledge Base Question Answering

knowledgebasedsearch

llama-recipes

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger

machinelearningpractice

Some practices using statistical machine learning technique based on some dataset. (notes and doing from scratch)

math

The MATH Dataset (NeurIPS 2021)

meb-net

"Multiple Expert Brainstorming for Domain Adaptive Person Re-identification", ECCV 2020

mind2web

[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web"

mini_dev

moviereconline

使用Django2.2+MySQL+spark实现在线电影推荐系统。其中MySQL部分支持在线计算，spark支持离线计算。

msmarco

website for MS Marco

multiwoz

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)