ilyalasy

ilyalasy's Stars

• karpathy/llm.c

  LLM training in simple, raw C/CUDA

  Language:Cuda24.4k2.8k

• teacherpeterpan/Logic-LLM

  The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"

  Language:C26041

• IBM/ModuleFormer

  ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward experts. We released a collection of ModuleFormer-based Language Models (MoLM) ranging in scale from 4 billion to 8 billion parameters.

  Language:Python21612

• EleutherAI/elk

  Keeping language models honest by directly eliciting knowledge encoded in their activations.

  Language:Python18633

• princeton-nlp/SWE-agent

  [NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.

  Language:Python13.7k1.4k

• microsoft/LMOps

  General technology for enabling AI capabilities w/ LLMs and MLLMs

  Language:Python3.7k282

• noamgat/lm-format-enforcer

  Enforce the output format (JSON Schema, Regex etc) of a language model

  Language:Python1.5k69

• SakanaAI/evolutionary-model-merge

  Official repository of Evolutionary Optimization of Model Merging Recipes

  Language:Python1.2k90

• lucidrains/soft-moe-pytorch

  Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

  Language:Python2459

• IST-DASLab/qmoe

  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".

  Language:Python26222

• sergree/matchering

  🎚️ Open Source Audio Matching and Mastering

  Language:Python1.8k184

• mlfoundations/task_vectors

  Editing Models with Task Arithmetic

  Language:Python42937

• arcee-ai/mergekit

  Tools for merging pretrained large language models.

  Language:Python4.8k439

• pjlab-sys4nlp/llama-moe

  ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

  Language:Python88346

• lucidrains/st-moe-pytorch

  Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch

  Language:Python29325

• ilyalasy/moe-routing

  Analysis of token routing for different implementations of Mixture of Experts

  Language:Jupyter Notebook8

• casper-hansen/AutoAWQ

  AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

  Language:Python1.8k212

• koxudaxi/datamodel-code-generator

  Pydantic model and dataclasses.dataclass generator for easy conversion of JSON, OpenAPI, JSON Schema, and YAML data sources.

  Language:Python2.8k304

• karpathy/minbpe

  Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

  Language:Python9.2k865

• XueFuzhao/OpenMoE

  A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

  Language:Python1.4k71

• THU-KEG/KEPLER

  Source code for TACL paper "KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation".

  Language:Python19623

• facebookresearch/LAMA

  LAnguage Model Analysis

  Language:Python1.4k184

• hadasah/btm

  Language:Python716

• deepseek-ai/DeepSeek-MoE

  DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

  Language:Python1k49

• OFA-Sys/Ditto

  A self-ailgnment method for role-play. Benchmark for role-play. Resources for "Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment".

  Language:Jupyter Notebook16417

• dojoteef/storium-gpt2

  Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loop Story Generation"

  Language:Python393

• fabrahman/char-centric-story

  Codebase for character-centric story understanding

  Language:Jupyter Notebook101

• BerriAI/litellm

  Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

  Language:Python13.9k1.6k

• ianarawjo/ChainForge

  An open-source visual programming environment for battle-testing prompts to LLMs.

  Language:TypeScript2.3k179

• c32168/dyntamic

  Generate pydantic models from JSON Schema

  Language:Python214