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