foundation-model-stack / fms-hf-tuning
π Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.
β38Updated this week
Alternatives and similar repositories for fms-hf-tuning:
Users that are interested in fms-hf-tuning are comparing it to the libraries listed below
- Estimate resources needed to train LLMsβ13Updated last month
- π¦ Unitxt: a python library for getting data fired up and set for training and evaluationβ181Updated this week
- Python library for Synthetic Data Generationβ35Updated this week
- Dolomite Engine is a library for pretraining/finetuning LLMsβ44Updated this week
- IBM development fork of https://github.com/huggingface/text-generation-inferenceβ60Updated 3 months ago
- InstructLab Training Library - Efficient Fine-Tuning with Message-Format Dataβ30Updated this week
- codebase release for EMNLP2023 paper publicationβ19Updated last year
- Supervised instruction finetuning for LLM with HF trainer and Deepspeedβ34Updated last year
- A package dedicated for running benchmark agreement testingβ16Updated 4 months ago
- The Granite Guardian models are designed to detect risks in prompts and responses.β72Updated last week
- β24Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignmentβ55Updated 6 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimizationβ59Updated last year
- Official repo for NAACL 2024 Findings paper "LeTI: Learning to Generate from Textual Interactions."β63Updated last year
- β74Updated last year
- Reward Model framework for LLM RLHFβ61Updated last year
- β48Updated 4 months ago
- Lightweight demos for finetuning LLMs. Powered by π€ transformers and open-source datasets.β73Updated 5 months ago
- Benchmark suite for LLMs from Fireworks.aiβ70Updated last month
- β33Updated 8 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absoluteβ¦β49Updated 8 months ago
- A framework for pitting LLMs against each other in an evolving library of games ββ32Updated this week
- β66Updated 10 months ago
- LLM attention pattern visualizerβ10Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.β117Updated last year
- β22Updated last year
- a pipeline for using api calls to agnostically convert unstructured data into structured training dataβ30Updated 6 months ago
- Improving Text Embedding of Language Models Using Contrastive Fine-tuningβ61Updated 7 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked promptsβ24Updated last year
- β32Updated 9 months ago