hijkzzz's Stars
BIT-aerial-robotics/AquaML
Developer-Y/cs-video-courses
List of Computer Science courses with video lectures.
kvcache-ai/Mooncake
Mooncake is the serving platform for icon Kimi, a leading LLM service provided by icon Moonshot AI.
OpenAccess-AI-Collective/axolotl
Go ahead and axolotl questions
unslothai/unsloth
Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
NVIDIA/TensorRT-Model-Optimizer
TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
meta-llama/llama-recipes
Scripts for fine-tuning Meta Llama3 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 Llama3 for WhatsApp & Messenger.
OpenBMB/MiniCPM-V
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
InternLM/xtuner
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
multimodal-art-projection/MAP-NEO
BradyFU/Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
langgenius/dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
riiswa/kanrl
Kolmogorov-Arnold Network for Reinforcement Leaning, initial experiments
Johnshall/Shadowrocket-ADBlock-Rules-Forever
提供多款 Shadowrocket 规则,拥有强劲的广告过滤功能。每日8时重新构建规则。
GMOogway/shadowrocket-rules
小火箭规则🚀,小火箭配置,shadowrocket规则,shadowrocket rules,最全面的直连(DIRECT)、代理(PROXY)、屏蔽(REJECT)规则,自动构建,每日更新
jondurbin/airoboros
Customizable implementation of the self-instruct paper.
lm-sys/arena-hard-auto
Arena-Hard-Auto: An automatic LLM benchmark.
jzhang38/LongMamba
Some preliminary explorations of Mamba's context scaling.
AntNLP/nope_head_scale
hsiehjackson/RULER
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
OpenNLPLab/TransnormerLLM
Official implementation of TransNormerLLM: A Faster and Better LLM
sustcsonglin/flash-linear-attention
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
XuezheMax/megalodon
Reference implementation of Megalodon 7B model
open-compass/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
mit-han-lab/streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
openai/simple-evals
THUDM/LongBench
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
gkamradt/LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
ContextualAI/gritlm
Generative Representational Instruction Tuning
TencentARC/LLaMA-Pro
[ACL 2024] Progressive LLaMA with Block Expansion.