rawsh-rubrik's Stars
zefang-liu/AdaMoLE
AdaMoLE: Adaptive Mixture of LoRA Experts
quanshr/DMoERM
[ACL2024 Findings]DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling
jie040109/MLAE
The official PyTorch implementation of the paper "MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning"
GCYZSL/MoLA
MediaBrain-SJTU/MING
明医 (MING):中文医疗问诊大模型
Ablustrund/LoRAMoE
LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment
Leeroo-AI/mergoo
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
EricLBuehler/xlora
X-LoRA: Mixture of LoRA Experts
karpathy/LLM101n
LLM101n: Let's build a Storyteller
SkunkworksAI/hydra-moe
TUDB-Labs/mLoRA
An Efficient "Factory" to Build Multiple LoRA Adapters
for-ai/parameter-efficient-moe
spcl/MRAG
Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"
Aider-AI/aider
aider is AI pair programming in your terminal
explodinggradients/ragas
Supercharge Your LLM Application Evaluations 🚀
jlmelville/uwot
An R package implementing the UMAP dimensionality reduction method.
raphaelsty/knowledge
Open-source personal bookmarks search engine
thomasahle/dspy
DSPy: The framework for programming—not prompting—foundation models
srush/Triton-Puzzles
Puzzles for learning Triton
genomoncology/FuzzTypes
Pydantic extension for annotating autocorrecting fields.
neuml/txtai
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
onyx-dot-app/onyx
Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.
booydar/recurrent-memory-transformer
[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.
securitykiss-com/rfw
Remote Firewall as a web service. REST API for iptables.
primeqa/primeqa
The prime repository for state-of-the-art Multilingual Question Answering research and development.
sebastian-hofstaetter/colberter
ContextualAI/HALOs
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
AnswerDotAI/RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
stanfordnlp/dspy
DSPy: The framework for programming—not prompting—language models
huggingface/candle
Minimalist ML framework for Rust