yuchenlin / LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
☆858Updated 4 months ago
Related projects: ⓘ
- Code for fine-tuning Platypus fam LLMs using LoRA☆625Updated 7 months ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,306Updated 5 months ago
- LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.☆561Updated 8 months ago
- Extend existing LLMs way beyond the original training length with constant memory usage, without retraining☆657Updated 5 months ago
- LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions☆810Updated last year
- ☆1,194Updated this week
- Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".☆1,077Updated 8 months ago
- A library for advanced large language model reasoning☆1,124Updated 2 weeks ago
- [ICLR 2024] Lemur: Open Foundation Models for Language Agents☆530Updated 10 months ago
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,436Updated this week
- Official repository for LongChat and LongEval☆504Updated 3 months ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆508Updated 6 months ago
- LOMO: LOw-Memory Optimization☆974Updated 2 months ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆594Updated 3 months ago
- Measuring Massive Multitask Language Understanding | ICLR 2021☆1,148Updated last year
- PaL: Program-Aided Language Models (ICML 2023)☆462Updated last year
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆572Updated last month
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆758Updated 2 months ago
- Customizable implementation of the self-instruct paper.☆1,004Updated 6 months ago
- ☆338Updated last year
- Finetuning Large Language Models on One Consumer GPU in Under 4 Bits☆696Updated 3 months ago
- ☆1,109Updated 4 months ago
- A framework for the evaluation of autoregressive code generation language models.☆776Updated this week
- A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)☆1,063Updated 8 months ago
- Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"☆1,041Updated 6 months ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,352Updated 6 months ago
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,021Updated 8 months ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆1,451Updated last month
- Run evaluation on LLMs using human-eval benchmark☆374Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆1,396Updated this week