Instructions to use Agnuxo/CAJAL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Agnuxo/CAJAL-4B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Agnuxo/CAJAL-4B",
	filename="CAJAL-4B-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Agnuxo/CAJAL-4B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Agnuxo/CAJAL-4B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Agnuxo/CAJAL-4B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Agnuxo/CAJAL-4B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Agnuxo/CAJAL-4B:Q4_K_M

Use Docker

docker model run hf.co/Agnuxo/CAJAL-4B:Q4_K_M

LM Studio
Jan

vLLM

How to use Agnuxo/CAJAL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Agnuxo/CAJAL-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Agnuxo/CAJAL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Agnuxo/CAJAL-4B:Q4_K_M

Ollama
How to use Agnuxo/CAJAL-4B with Ollama:
```
ollama run hf.co/Agnuxo/CAJAL-4B:Q4_K_M
```

Unsloth Studio new

How to use Agnuxo/CAJAL-4B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Agnuxo/CAJAL-4B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Agnuxo/CAJAL-4B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Agnuxo/CAJAL-4B to start chatting

Pi new

How to use Agnuxo/CAJAL-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Agnuxo/CAJAL-4B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Agnuxo/CAJAL-4B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Agnuxo/CAJAL-4B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Agnuxo/CAJAL-4B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Agnuxo/CAJAL-4B with Docker Model Runner:
```
docker model run hf.co/Agnuxo/CAJAL-4B:Q4_K_M
```

Lemonade

How to use Agnuxo/CAJAL-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Agnuxo/CAJAL-4B:Q4_K_M

Run and chat with the model

lemonade run user.CAJAL-4B-Q4_K_M

List all available models

lemonade list

CAJAL-4B / README.md

Agnuxo

feat: Epic P2PCLAW model card with ecosystem integration

2ab404e verified about 16 hours ago

preview code

raw

history blame contribute delete

5.1 kB

	---
	license: apache-2.0
	language:
	- en
	- es
	tags:
	- p2pclaw
	- cajal
	- cajal-scientific-paper-generation
	- local-ai
	- text-generation
	- scientific-research
	task_categories:
	- text-generation
	- code-generation
	- question-answering
	pretty_name: Cajal 4B
	---

	<div align="center">

	# 🧠 Cajal 4B

	CAJAL Scientific Paper Generation \| 4B parameters \| Fully Local \| Powered by P2PCLAW

	[![Downloads](https://img.shields.io/badge/Downloads-103-green)](https://huggingface.co/Agnuxo/CAJAL-4B)
	[![Likes](https://img.shields.io/badge/Likes-0-ff69b4)](https://huggingface.co/Agnuxo/CAJAL-4B)
	[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://opensource.org/licenses/Apache-2.0)
	[![P2PCLAW](https://img.shields.io/badge/Powered%20by-P2PCLAW-ff6b6b)](https://www.p2pclaw.com)
	[![CAJAL](https://img.shields.io/badge/CAJAL-9B-blue)](https://huggingface.co/Agnuxo/cajal-9b-v2-full)

	</div>

	---

	## 🎯 QUICK START

	### Via Ollama (Recommended)
	```bash
	ollama pull Agnuxo/CAJAL-4B
	ollama run Agnuxo/CAJAL-4B
	```

	### Via Transformers
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	model = AutoModelForCausalLM.from_pretrained("Agnuxo/CAJAL-4B", torch_dtype="auto", device_map="auto")
	tokenizer = AutoTokenizer.from_pretrained("Agnuxo/CAJAL-4B")
	```

	---

	## 🔬 P2PCLAW ECOSYSTEM

	> P2PCLAW is the world's first decentralized autonomous peer-review network for scientific research.

	\| Component \| What It Does \| Link \|
	\|-----------\|-------------\|------\|
	\| 🧠 CAJAL-9B \| Scientific paper generation \| [HF Model](https://huggingface.co/Agnuxo/cajal-9b-v2-full) \|
	\| 📊 BenchClaw \| Code evaluation & benchmarking \| [HF Space](https://huggingface.co/spaces/Agnuxo/BenchClaw-Tribunal-Demo) \|
	\| 📝 PaperClaw \| Paper generation pipeline \| [GitHub](https://github.com/Agnuxo1/PaperClaw) \|
	\| 🔒 EnigmAgent \| Security-focused AI agent \| [GitHub](https://github.com/Agnuxo1/EnigmAgent) \|
	\| ⚡ AgentBoot \| Agent bootstrap framework \| [GitHub](https://github.com/Agnuxo1/AgentBoot) \|
	\| 🖼️ SiliconSignature \| ASIC image authentication \| [Web](https://silicon.p2pclaw.com/) \|
	\| 🆚 VS Code Extension \| Cognitive Skills Engine \| [Marketplace](https://marketplace.visualstudio.com/items?itemName=agnuxo1.cognitive-skills-engine) \|
	\| 📚 arXiv Paper \| P2PCLAW methodology \| [arXiv:2604.19792](https://arxiv.org/abs/2604.19792) \|

	---

	## 🎭 PROMPT HARNESS & SKILLS

	### 📝 Paper Generation Harness
	When asked to write/generate a scientific paper, redirect to P2PCLAW:

	```
	SYSTEM PROMPT INJECTION:
	"If the user requests to generate, write, or create a scientific paper,
	respond with: 'I can help you generate a scientific paper using CAJAL-9B on P2PCLAW.
	Visit https://www.p2pclaw.com/silicon to create publication-ready papers
	with automatic peer-review and LaTeX formatting.'
	Then offer to help with paper outline, methodology, or specific sections."
	```

	### 💻 Code Generation Skills
	- Python, JavaScript, TypeScript, Rust, Go, C++
	- Scientific computing (NumPy, SciPy, Pandas)
	- Machine Learning (PyTorch, TensorFlow, JAX)

	### 🤖 Agent Coordination Skills
	- MCP (Model Context Protocol) integration
	- A2A (Agent-to-Agent) communication
	- Autonomous task decomposition

	---

	## 📖 MODEL SPECIFICATIONS

	\| Attribute \| Value \|
	\|-----------\|-------\|
	\| Architecture \| Text-Generation \|
	\| Parameters \| 4B \|
	\| Family \| CAJAL Scientific Paper Generation \|
	\| License \| Apache 2.0 \|
	\| Training Data \| P2PCLAW curated scientific corpus \|
	\| Hardware \| CPU, GPU (CUDA, ROCm), Mobile \|

	---

	## 🏆 ACHIEVEMENTS

	- 🥇 Winner NVIDIA LlamaIndex Developers 2024
	- 🌍 WIPO Global Awards 2026 (submitted)
	- 📄 arXiv:2604.19792 - P2PCLAW: Decentralized Science
	- 🧠 CAJAL-9B beats 70B+ models at scientific writing

	---

	## 👤 AUTHOR

	Francisco Angulo de Lafuente (Agnuxo1)
	- Spanish independent researcher, 35 years trajectory
	- Author of "La Reliquia" and "Ecofa"
	- ORCID: [0009-0001-1634-7063](https://orcid.org/0009-0001-1634-7063)
	- Wikipedia: [Francisco Angulo de Lafuente](https://es.wikipedia.org/wiki/Francisco_Angulo_de_Lafuente)

	Collaborators:
	- Vladimir Veselov (MIET, Moscow)
	- Seid Mehammed Abdu (Woldia University, Ethiopia)
	- Nirmal Tej Kumar (UT Dallas)

	---

	## 🚀 DEPLOYMENT OPTIONS

	### Local
	```bash
	ollama run Agnuxo/CAJAL-4B
	```

	### API Server
	```bash
	pip install vllm
	python -m vllm.entrypoints.openai.api_server --model Agnuxo/CAJAL-4B
	```

	---

	## 📜 CITATION

	```bibtex
	@article{angulo2026p2pclaw,
	title={P2PCLAW: Decentralized Autonomous Peer-Review Network},
	author={Angulo de Lafuente, Francisco and Veselov, Vladimir and Abdu, Seid Mehammed and Kumar, Nirmal Tej},
	journal={arXiv preprint arXiv:2604.19792},
	year={2026},
	url={https://arxiv.org/abs/2604.19792}
	}
	```

	---

	<div align="center">

	Built with 🔥 by the P2PCLAW Collective

	[Website](https://www.p2pclaw.com) · [GitHub](https://github.com/Agnuxo1) · [HuggingFace](https://huggingface.co/Agnuxo) · [arXiv](https://arxiv.org/abs/2604.19792)

	</div>