Sen's starred repositories

v2rayN

A GUI client for Windows, support Xray core and v2fly core and others

Language:C#License:GPL-3.0Stargazers:67564Issues:720Issues:4718

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

Language:PythonLicense:Apache-2.0Stargazers:31621Issues:200Issues:4899

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Language:PythonLicense:Apache-2.0Stargazers:27581Issues:225Issues:4632

TranslucentTB

A lightweight utility that makes the Windows taskbar translucent/transparent.

Language:C++License:GPL-3.0Stargazers:15574Issues:222Issues:977

mamba

Mamba SSM architecture

Language:PythonLicense:Apache-2.0Stargazers:12702Issues:101Issues:511

llama-recipes

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:11882Issues:96Issues:340

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Language:SystemVerilogStargazers:6959Issues:68Issues:23

tree-of-thought-llm

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Language:PythonLicense:MITStargazers:4638Issues:122Issues:54

duckling

Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.

Language:HaskellLicense:NOASSERTIONStargazers:4060Issues:80Issues:404

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Language:PythonLicense:Apache-2.0Stargazers:2557Issues:24Issues:27

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

Language:PythonLicense:Apache-2.0Stargazers:2049Issues:19Issues:81

EasyEdit

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

Language:Jupyter NotebookLicense:MITStargazers:1801Issues:22Issues:307

MOSS-RLHF

MOSS-RLHF

Language:PythonLicense:Apache-2.0Stargazers:1272Issues:34Issues:52

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Language:PythonLicense:MITStargazers:1229Issues:24Issues:44

Triton-Puzzles

Puzzles for learning Triton

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1008Issues:10Issues:10

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

Language:PythonLicense:NOASSERTIONStargazers:704Issues:10Issues:55

lumos

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

Language:PythonLicense:MITStargazers:442Issues:10Issues:7

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

openlogprobs

Extract full next-token probabilities via language model APIs

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.

Language:PythonLicense:Apache-2.0Stargazers:185Issues:7Issues:12

VCD

[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

Language:PythonLicense:Apache-2.0Stargazers:182Issues:6Issues:21

SeaLLMs

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

CLEX

[ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models

Language:PythonLicense:MITStargazers:72Issues:4Issues:8

ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"

Language:PythonLicense:MITStargazers:57Issues:3Issues:2

CUT

Source code of "Reasons to Reject? Aligning Language Models with Judgments"

Language:PythonLicense:Apache-2.0Stargazers:55Issues:1Issues:4

GSM-Plus

GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.

Model-Editing-Hurt

Model Editing Can Hurt General Abilities of Large Language Models

CaRing

Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs

Language:PythonLicense:MITStargazers:20Issues:5Issues:0

RemeMo

[EMNLP 2023] Once Upon a *Time* in *Graph*: Relative-Time Pretraining for Complex Temporal Reasoning

Language:PythonLicense:MITStargazers:17Issues:6Issues:0

minGPU

Minimal example illustrating how to use multiple GPUs in PyTorch

Language:PythonStargazers:7Issues:2Issues:0