instruction-tuning

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

machine-learning deep-learning embodied multi-modality artificial-inteligence embodied-ai egocentric-vision gpt-4 foundation-models large-scale-models visual-language-learning chatgpt instruction-tuning apple-vision-pro

Updated Jul 29, 2023
Python

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. Meanwhile, we created a new branch to build a Tabular LLM.（我们分别统一了丰富的IFT数据（如CoT数据，目前仍不断扩充）、多种训练效率方法（如lora，p-tuning）以及多种LLMs，三个层面上的接口，打造方便研究人员上手的LLM-IFT研究平台。同时tabular_llm分支构建了面向表格智能任务的LLM。

tabular-data pytorch llama lora moss alpaca cot tabul tabular-model p-tuning llm parameter-efficient chatgpt instruction-tuning chatglm

Updated Jul 26, 2023
Jupyter Notebook

yangjianxin1 / Firefly

Star

Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)，支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型

bloom llama gpt lora alpaca peft baichuan llm instruction-tuning qlora baichuan-7b internlm baichuan-13b llama2 llama-2

Updated Jul 28, 2023
Python

X-PLUG / mPLUG-Owl

Star

mPLUG-Owl🦉: Modularization Empowers Large Language Models with Multimodality

Updated Jul 22, 2023
Python

DSXiangLi / DecryptPrompt

Star

总结Prompt&LLM论文，开源数据&模型，AIGC应用

prompt papers demonstration zero-shot-learning few-shot-learning prompt-tuning in-context-learning aigc llm chain-of-thought chatgpt instruction-tuning llm-agent

Updated Jul 28, 2023

yaodongC / awesome-instruction-dataset

Star

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

llama datasets language-model gpt-3 instruction-following gpt-4 awsome-lists instruction-tuning

Updated Jul 25, 2023

bigscience-workshop / xmtf

Star

Crosslingual Generalization through Multitask Finetuning

bloom language-models zero-shot-learning multitask-learning t5 multilingual-nlp large-language-models instruction-tuning bloomz mt0

Updated Jun 22, 2023
Jupyter Notebook

zjunlp / KnowLM

Star

An Open-sourced Knowledgable Large Language Model Family.

Updated Jul 29, 2023
Python

atfortes / LLM-Reasoning-Papers

Star

Collection of papers and resources on Reasoning in Large Language Models (LLMs), including Chain-of-Thought (CoT), Instruction-Tuning, and others.

awesome prompt lm question-answering datasets language-models reasoning commonsense-reasoning cot logical-reasoning symbolic-reasoning gpt3 prompt-learning in-context-learning prompt-engineering chain-of-thought arithmetic-reasoning chatgpt instruction-tuning

Updated Jun 20, 2023

HugAILab / HugNLP

Star

HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊

natural-language-processing deep-learning transformers pytorch information-extraction few-shot-learning code-understanding large-language-models prompt-based-learning instruction-tuning hugchat

Updated May 9, 2023
Python

RenzeLou / awesome-instruction-learning

Star

Papers and Datasets on Instruction Learning / Instruction Tuning. ✨✨✨

prompt survey awesome-list datasets instruction paper-list pretrained-language-model in-context-learning large-language-models instruction-tuning instruction-learning

Updated Jul 23, 2023
Python

ictnlp / BayLing

Star

“百聆”是一个具有增强的语言对齐的英语/中文大语言模型，具有优越的英语/中文能力，在多项测试中取得ChatGPT 90%的性能。BayLing is an English/Chinese LLM equipped with advanced language alignment, showing superior capability in English/Chinese generation, instruction following and multi-turn interaction.