LAION-AI / blade2blade
Adversarial Training and SFT for Bot Safety Models
☆39Updated last year
Related projects ⓘ
Alternatives and complementary repositories for blade2blade
- Experiments with generating opensource language model assistants☆97Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- Multi-Domain Expert Learning☆67Updated 9 months ago
- ☆46Updated this week
- Tools for content datamining and NLP at scale☆42Updated 5 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- Code for NeurIPS LLM Efficiency Challenge☆54Updated 7 months ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- Implementation of "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"☆42Updated last week
- Embedding Recycling for Language models☆38Updated last year
- ☆48Updated 2 weeks ago
- ☆27Updated 5 months ago
- ☆37Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- Advanced Reasoning Benchmark Dataset for LLMs☆45Updated last year
- For experiments involving instruct gpt. Currently used for documenting open research questions.☆71Updated 2 years ago
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆50Updated this week
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆37Updated 7 months ago
- QLoRA for Masked Language Modeling☆20Updated last year
- Lightweight demos for finetuning LLMs. Powered by 🤗 transformers and open-source datasets.☆64Updated last month
- A library for squeakily cleaning and filtering language datasets.☆45Updated last year
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated last year
- ☆33Updated 6 months ago
- QLoRA with Enhanced Multi GPU Support☆36Updated last year
- Code repository for the c-BTM paper☆105Updated last year
- A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.☆32Updated 2 months ago