hunterlang's Stars
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
fish-shell/fish-shell
The user-friendly command line shell.
seatgeek/fuzzywuzzy
Fuzzy String Matching in Python
duckduckgo/duckduckgo
DuckDuckGo Instant Answer Infrastructure
holman/boom
Motherfucking TEXT SNIPPETS! On the COMMAND LINE!
ShannonAI/service-streamer
Boosting your Web Services of Deep Learning Applications.
RLHFlow/RLHF-Reward-Modeling
Recipes to train reward model for RLHF.
duckduckgo/zeroclickinfo-goodies
DuckDuckGo Instant Answers based on Perl & JavaScript
yoonkim/lstm-char-cnn
LSTM language model with CNN over characters
RLHFlow/Online-RLHF
A recipe for online RLHF and online iterative DPO.
r-three/t-few
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
ciphermodelabs/ciphercore
User-friendly secure computation engine based on secure multi-party computation
kipgparker/soft-prompt-tuning
duckduckgo/zeroclickinfo-fathead
DuckDuckGo Instant Answers based on keyword data files
clinicalml/TabLLM
JieyuZ2/wrench
[NeurIPS 2021] WRENCH: Weak supeRvision bENCHmark
ilyaraz/ot_estimators
Implementations of several fast approximate algorithms for geometric optimal transport (OT)
probcomp/LLaMPPL
A domain-specific probabilistic programming language for modeling and inference with language models
clinicalml/co-llm
Co-LLM: Learning to Decode Collaboratively with Multiple Language Models
microsoft/denoised-smoothing
Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
microsoft/statopt
Statistical adaptive stochastic optimization methods
belindal/TaskBench500
Suite of 500 procedurally-generated NLP tasks to study language model adaptability
clinicalml/cotrain-prompting
Code for co-training large language models (e.g. T0) with smaller ones (e.g. BERT) to boost few-shot performance
hunterlang/weaksup-subset-selection
Subset selection / data pruning for weak supervision
aroman/TNBT
The idealism of youth...
aroman/telecomando
Web-based remote control for Linux
hunterlang/vllm-mixture
fork of vllm 0.2.6 with support for mixing language model probabilities. allows for fast decoding from a mixture of two models.