Instructions to use jarohullowicki/Jjfp-core-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jarohullowicki/Jjfp-core-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jarohullowicki/Jjfp-core-v1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jarohullowicki/Jjfp-core-v1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jarohullowicki/Jjfp-core-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jarohullowicki/Jjfp-core-v1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jarohullowicki/Jjfp-core-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jarohullowicki/Jjfp-core-v1
- SGLang
How to use jarohullowicki/Jjfp-core-v1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "jarohullowicki/Jjfp-core-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jarohullowicki/Jjfp-core-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "jarohullowicki/Jjfp-core-v1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jarohullowicki/Jjfp-core-v1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jarohullowicki/Jjfp-core-v1 with Docker Model Runner:
docker model run hf.co/jarohullowicki/Jjfp-core-v1
JFP-Core-v1 — Jaro Flash Protocol Aligned Model
What is this?
JFP-Core-v1 is the first model configuration aligned with the Jaro Flash Protocol (JFP) v16E.0.0 — a deterministic multi-agent AI execution framework developed by Jarosław Kuchta.
This is not a standard language model. It is a protocol-governed AI engine designed for auditable, traceable, and reproducible AI applications.
Key Properties
- Deterministic execution — consistent outputs for structured inputs
- JFP constitutional layer — built-in rules that cannot be overridden by user prompts
- Reduced hallucination — refusal protocol replaces confabulation
- Audit trail ready — every output is traceable and explainable
- Anti-drift design — behavior stays within defined protocol boundaries
- VOQL compatible — native support for VIKI Operational Query Language
Intended Use
- Auditable enterprise AI pipelines
- Multi-agent orchestration systems
- Compliance-sensitive applications (legal, medical, financial)
- JFP-standard compatible tooling
Not Intended For
- General-purpose chat
- Creative/open-ended generation without protocol constraints
- Applications requiring unpredictable or exploratory outputs
Base Model
Built as a fine-tune configuration for Qwen/Qwen2.5-1.5B-Instruct.
Lightweight local agent designed for continuous learning via JFP-BC constitution.
Tools
This model includes a native tool specification. See tools.json in this repository.
Supported tools:
code_execution— sandboxed Python/bash executionfile_operations— read/write within JFP boundariesvoql_query— VIKI Operational Query Language queriesagent_dispatch— sub-agent communication within VIKI ecosystemaudit_log— immutable action loggingapi_call— external REST API calls (whitelist only)jfp_validate— schema validation against JFP standard
Limitations
- Requires JFP-compliant input format for optimal performance
- Not designed for open-ended creative tasks
- Commercial use requires separate licensing agreement
Protocol
Built on JFP v16E.0.0 — part of the VIKI ecosystem. Author: Jarosław Kuchta | GitHub
License
cc-by-nc-4.0 — Free for non-commercial use. Commercial licensing: contact the author.
Citation
@misc{kuchta2026jfp,
author = {Jarosław Kuchta},
title = {Jaro Flash Protocol (JFP) v16E.0.0},
year = {2026},
publisher = {Hugging Face},
url = {https://huggingface.co/jarohullowicki/Jjfp-core-v1}
}
- Downloads last month
- 67