huggingface / alignment-handbookLinks
Robust recipes to align language models with human and AI preferences
☆5,417Updated 2 months ago
Alternatives and similar repositories for alignment-handbook
Users that are interested in alignment-handbook are comparing it to the libraries listed below
Sorting:
- Tools for merging pretrained large language models.☆6,436Updated last week
- PyTorch native post-training library☆5,576Updated last week
- A framework for few-shot evaluation of language models.☆10,553Updated last week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,918Updated last week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,715Updated this week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,896Updated 3 months ago
- Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models …☆2,533Updated 3 weeks ago
- Go ahead and axolotl questions☆10,753Updated this week
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆4,165Updated 4 months ago
- AllenAI's post-training codebase☆3,284Updated this week
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆2,068Updated last year
- The hub for EleutherAI's work on interpretability and learning dynamics☆2,661Updated 5 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,771Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,146Updated 2 months ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,399Updated last year
- Benchmarking large language models' complex reasoning ability with chain-of-thought prompting☆2,756Updated last year
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,792Updated 4 months ago
- A quick guide (especially) for trending instruction finetuning datasets☆3,301Updated last year
- Accessible large language models via k-bit quantization for PyTorch.☆7,737Updated last week
- A curated list of reinforcement learning with human feedback resources (continually updated)☆4,200Updated last month
- Train transformer language models with reinforcement learning.☆16,228Updated this week
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,725Updated last year
- Modeling, training, eval, and inference code for OLMo☆6,100Updated 2 weeks ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,658Updated last year
- An Open-source Toolkit for LLM Development☆2,791Updated 9 months ago
- A modular RL library to fine-tune language models to human preferences☆2,363Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,078Updated this week
- ☆4,103Updated last year
- A library for advanced large language model reasoning☆2,300Updated 5 months ago
- Curated list of datasets and tools for post-training.☆3,850Updated 3 months ago