huggingface / alignment-handbook
Robust recipes to align language models with human and AI preferences
☆5,056Updated 3 months ago
Alternatives and similar repositories for alignment-handbook:
Users that are interested in alignment-handbook are comparing it to the libraries listed below
- Tools for merging pretrained large language models.☆5,424Updated this week
- A framework for few-shot evaluation of language models.☆8,270Updated this week
- Train transformer language models with reinforcement learning.☆12,591Updated this week
- PyTorch native post-training library☆4,994Updated this week
- Accessible large language models via k-bit quantization for PyTorch.☆6,793Updated this week
- AllenAI's post-training codebase☆2,804Updated this week
- Go ahead and axolotl questions☆8,882Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆11,810Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆6,830Updated 8 months ago
- General technology for enabling AI capabilities w/ LLMs and MLLMs☆3,888Updated this week
- Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Ad…☆6,040Updated 6 months ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,601Updated last year
- ☆4,071Updated 9 months ago
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆17,795Updated this week
- An Open-source Toolkit for LLM Development☆2,762Updated 2 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,303Updated 9 months ago
- Aligning pretrained language models with instruction data generated by themselves.☆4,307Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,884Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,752Updated last month
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,685Updated 2 months ago
- Large Language Model Text Generation Inference☆9,881Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,554Updated last week
- SGLang is a fast serving framework for large language models and vision language models.☆11,970Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,300Updated 10 months ago
- Reference implementation for DPO (Direct Preference Optimization)☆2,445Updated 7 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,299Updated 2 weeks ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,394Updated last week
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,703Updated last year
- [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which ach…☆4,939Updated last week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,460Updated 8 months ago