foundation-model-stack / fms-hf-tuning
🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.
☆40Updated 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
- 🦄 Unitxt: a python library for getting data fired up and set for training and evaluation☆187Updated this week
- Estimate resources needed to train LLMs☆13Updated last month
- IBM development fork of https://github.com/huggingface/text-generation-inference☆60Updated 4 months ago
- Dolomite Engine is a library for pretraining/finetuning LLMs☆49Updated this week
- Python library for Synthetic Data Generation☆41Updated this week
- codebase release for EMNLP2023 paper publication☆19Updated last year
- Benchmark suite for LLMs from Fireworks.ai☆70Updated 2 months ago
- Train, tune, and infer Bamba model☆88Updated this week
- InstructLab Training Library - Efficient Fine-Tuning with Message-Format Data☆35Updated this week
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated 11 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆22Updated 2 weeks ago
- Supervised instruction finetuning for LLM with HF trainer and Deepspeed☆34Updated last year
- ☆28Updated 5 months ago
- Small and Efficient Mathematical Reasoning LLMs☆71Updated last year
- 🚀 Collection of libraries used with fms-hf-tuning to accelerate fine-tuning and training of large models.☆9Updated last week
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- vLLM adapter for a TGIS-compatible gRPC server.☆26Updated this week
- Shakespeare transformer fine-tuned to generate positive sentiment samples using RLHF☆10Updated 2 years ago
- Prune transformer layers☆68Updated 10 months ago
- Code for NeurIPS LLM Efficiency Challenge☆57Updated last year
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆34Updated 4 months ago
- ☆35Updated 9 months ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆30Updated 7 months ago
- ☆24Updated last year
- ☆15Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- ☆48Updated 5 months ago
- ☆37Updated 2 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆120Updated last year
- Aioli: A unified optimization framework for language model data mixing☆23Updated 3 months ago