Instructions to use batistado/QuorumGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use batistado/QuorumGuard with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("batistado/QuorumGuard", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from batistado/QuorumGuard: direct link, hf CLI and curl.
- Browser
- Download file 1.4 kB
-
https://huggingface.co/batistado/QuorumGuard/resolve/main/README.md
- Command line
-
hf download hf://batistado/QuorumGuard/README.md
-
curl -L -o README.md https://huggingface.co/batistado/QuorumGuard/resolve/main/README.md
1.4 kB
metadata
license: apache-2.0
library_name: transformers
tags:
- multi-agent-systems
- consensus
- tail-latency
- semantic-entropy
- llm-agents
- vllm
datasets:
- batistado/QuorumBench
base_model:
- Qwen/Qwen2.5-3B-Instruct
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2.5-Coder-14B-Instruct
- HuggingFaceTB/SmolLM2-1.7B-Instruct
- ibm-granite/granite-3.1-8b-instruct
QuorumGuard: Claim-Genealogy-Gated Hedged Quorums & Priority Dissent Preemption
- Benchmark Dataset:
batistado/QuorumBench - Interactive Simulator Space:
batistado/QuorumGuard-Explorer - Paper PDF (10 pages):
paper/main.pdf - Source Code & Paper:
github.com/batistado/quorumguard
QuorumGuard is a model-agnostic consensus controller and quantum-preemptive priority scheduler for asynchronous multi-agent LLM committees. It requires zero weight modifications and operates on pre-commitment option logits, provenance DAGs, and priority-preemptive decode quanta (Priority = -10 in both our live PyTorch MPS DynamicCache server and vLLM-compatible priority schedulers).
Install
pip install git+https://github.com/batistado/quorumguard.git
