cfoster0's Stars
InflectionAI/Inflection-Benchmarks
Public Inflection Benchmarks
moritztng/fltr
Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.
proger/hippogriff
Griffin MQA + Hawk Linear RNN Hybrid
louaaron/Score-Entropy-Discrete-Diffusion
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
corl-team/rebased
Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"
datadreamer-dev/DataDreamer
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
nerfstudio-project/gsplat
CUDA accelerated rasterization of gaussian splatting
UT-Austin-RPL/amago
a simple and scalable agent for training adaptive policies with sequence-based RL
flashinfer-ai/flashinfer
FlashInfer: Kernel Library for LLM Serving
punica-ai/punica
Serving multiple LoRA finetuned LLM as one
instructor-ai/instructor
structured outputs for llms
stanfordnlp/dspy
DSPy: The framework for programming—not prompting—language models
henrikbostrom/crepes
Python package for conformal prediction
google/rax
Rax is a Learning-to-Rank library written in JAX.
LaurentMazare/mamba.rs
vikhyat/moondream
tiny vision language model
fferflo/einx
Universal Tensor Operations in Einstein-Inspired Notation for Python.
hustvl/Vim
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
PrefectHQ/marvin
✨ Build AI interfaces that spark joy
sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
SHI-Labs/NATTEN
Neighborhood Attention Extension. Bringing attention to a neighborhood near you!
vikhyat/e_natten
Blazingly fast neighborhood attention
johnryan465/pscan
proger/accelerated-scan
Accelerated First Order Parallel Associative Scan
sustcsonglin/flash-linear-attention
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
PolyAI-LDN/pheme
cgarciae/einop
ggerganov/llama.cpp
LLM inference in C/C++
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.
langroid/langroid
Harness LLMs with Multi-Agent Programming