Pinned Repositories
alpaca-lora
Instruct-tune LLaMA on consumer hardware
AlpacaDataCleaned
Generate instructions with Claude and ChatGPT
chatbot-ui
A ChatGPT clone for running locally in your browser.
DHS-LLM-Workshop
DHS 2023 LLM Workshop by Sourab Mangrulkar
dynamodb-faiss-builder
Lambda function that creates a Faiss index for a DynamoDB table
eclair-agents
fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
shossain's Repositories
shossain/AlpacaDataCleaned
Generate instructions with Claude and ChatGPT
shossain/alpaca-lora
Instruct-tune LLaMA on consumer hardware
shossain/chatbot-ui
A ChatGPT clone for running locally in your browser.
shossain/DHS-LLM-Workshop
DHS 2023 LLM Workshop by Sourab Mangrulkar
shossain/dynamodb-faiss-builder
Lambda function that creates a Faiss index for a DynamoDB table
shossain/eclair-agents
shossain/fine-tune-mistral
Fine-tune mistral-7B on 3090s, a100s, h100s
shossain/gill
🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".
shossain/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
shossain/notebooks
Notebooks using the Hugging Face libraries 🤗
shossain/OpenDelta
A plug-and-play library for parameter-efficient-tuning (Delta Tuning)
shossain/pytho
shossain/llm_large_context
Large Context Transformers
shossain/LM-Infinite
Implementation of paper "LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models"
shossain/LongLM
LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
shossain/LongLoRA
Efficient long-context fine-tuning, supervised fine-tuning, LongQA dataset.
shossain/MemGPT
Teaching LLMs memory management for unbounded context 📚🦙
shossain/milsymbol
Military Symbols in JavaScript
shossain/OpenDevin
🐚 OpenDevin: Code Less, Make More
shossain/overwatch
shossain/PoSE
Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length
shossain/primer-research
shossain/rerope
Rectified Rotary Position Embeddings
shossain/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
shossain/tork
A distributed workflow engine
shossain/tork-web
Web UI for Tork Workflow Engine
shossain/trulens
Evaluation and Tracking for LLM Experiments
shossain/unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
shossain/whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation
shossain/yarn
YaRN: Efficient Context Window Extension of Large Language Models