bayjarvis

llm

Fine-tuning, DPO, RLHF, RLAIF on LLMs - Zephyr 7B GPTQ with 4-Bit Quantization, Mistral-7B-GPTQ

autonomous_agent

Autonomous Agent - Profiling, Memory, Planning, Action, Autogen, MemGPT

network_architecture

Network architecture - The Structured State Space for Sequence Modeling (S4) architecture, Mamba, BitNet Transformer

prompt

Prompt Optimization and Templates - Promptbreeder, Self-Discover

nanoTransformer

A PyTorch-based featuring an efficiently implemented Transformer model. The core of our attention mechanisms is powered by torch.einsum, ensuring clean, readable, and highly optimized tensor operations.

opengpts

recommendation_system

product quantization

reinforcement_learning

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs