alexrs / herd
Mixture of Expert (MoE) techniques for enhancing LLM performance through expert-driven prompt mapping and adapter combinations.
☆12Updated 7 months ago
Related projects: ⓘ
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆23Updated last year
- ☆29Updated 2 weeks ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 6 months ago
- ☆50Updated last month
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆34Updated 10 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆40Updated 8 months ago
- ☆22Updated 3 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆39Updated 3 weeks ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆34Updated 5 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 5 months ago
- Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)☆25Updated 6 months ago
- GoldFinch and other hybrid transformer components☆38Updated 2 months ago
- Repository for Skill Set Optimization☆12Updated last month
- [ICML 24 NGSM workshop] Associative Recurrent Memory Transformer implementation and scripts for training and evaluating☆26Updated last week
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 8 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆22Updated 6 months ago
- A repository for research on medium sized language models.☆71Updated 3 months ago
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆27Updated this week
- The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models…☆29Updated 7 months ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆33Updated last year
- SCREWS: A Modular Framework for Reasoning with Revisions☆26Updated 11 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated last year
- ReBase: Training Task Experts through Retrieval Based Distillation☆27Updated 2 months ago
- ☆45Updated 7 months ago
- Improving Text Embedding of Language Models Using Contrastive Fine-tuning☆54Updated last month
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆37Updated 3 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆15Updated 3 weeks ago
- Token-level adaptation of LoRA matrices for downstream task generalization.☆14Updated 5 months ago
- Byte-sized text games for code generation tasks on virtual environments☆17Updated 2 months ago