shossain's repositories
autogen
A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
LongLM
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Husky-v1
Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and knowledge-based reasoning tasks.
PIGEON
Code for the paper "PIGEON: Predicting Image Geolocations".
CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型
tork-web
Web UI for Tork Workflow Engine
OpenDevin
🐚 OpenDevin: Code Less, Make More
tork
A distributed workflow engine
DHS-LLM-Workshop
DHS 2023 LLM Workshop by Sourab Mangrulkar
geo-clip
This is an official PyTorch implementation of our NeurIPS 2023 paper "GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization"
trulens
Evaluation and Tracking for LLM Experiments
PoSE
Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length
whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
yarn
YaRN: Efficient Context Window Extension of Large Language Models
rerope
Rectified Rotary Position Embeddings
AlpacaDataCleaned
Generate instructions with Claude and ChatGPT
MemGPT
Teaching LLMs memory management for unbounded context 📚🦙
gill
🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".
LM-Infinite
Implementation of paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
milsymbol
Military Symbols in JavaScript
LongLoRA
Efficient long-context fine-tuning, supervised fine-tuning, LongQA dataset.
llm_large_context
Large Context Transformers
alpaca-lora
Instruct-tune LLaMA on consumer hardware
OpenDelta
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)