davanstrien / haiku-dpo
Using open source LLMs to build synthetic datasets for direct preference optimization
☆40Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for haiku-dpo
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- ☆40Updated 2 weeks ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆48Updated 4 months ago
- Set of scripts to finetune LLMs☆36Updated 7 months ago
- Code and data for "StructLM: Towards Building Generalist Models for Structured Knowledge Grounding" (COLM 2024)☆68Updated last month
- ☆24Updated last year
- Simple examples using Argilla tools to build AI☆40Updated this week
- ☆48Updated last year
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆77Updated 8 months ago
- ☆93Updated last month
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆61Updated 2 weeks ago
- Lightweight tools for quick and easy LLM demo's☆26Updated last month
- Codebase accompanying the Summary of a Haystack paper.☆72Updated 2 months ago
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆64Updated last month
- ☆20Updated 9 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Explore the use of DSPy for extracting features from PDFs 🔎☆33Updated 8 months ago
- Writing Blog Posts with Generative Feedback Loops!☆43Updated 8 months ago
- Tools to make language models a bit easier to use☆30Updated this week
- ☆64Updated 5 months ago
- ☆41Updated last month
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆37Updated 3 weeks ago
- Efficient few-shot learning with cross-encoders.☆40Updated 9 months ago
- QLoRA for Masked Language Modeling☆20Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- ☆33Updated 6 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆46Updated 2 months ago
- ☆27Updated 5 months ago
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated last month