Text Generation
GGUF
English
Italian
question-answering
articles
change management
qwen3.5
cpu-compatible
local-inference
faiss
qdrant
conversational
knowledge-base
Instructions to use robertolofaro/articles-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use robertolofaro/articles-model with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="robertolofaro/articles-model", filename="articles-Q4_K_M.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 robertolofaro/articles-model with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf robertolofaro/articles-model:Q4_K_M # Run inference directly in the terminal: llama-cli -hf robertolofaro/articles-model:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf robertolofaro/articles-model:Q4_K_M # Run inference directly in the terminal: llama-cli -hf robertolofaro/articles-model: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 robertolofaro/articles-model:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf robertolofaro/articles-model: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 robertolofaro/articles-model:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf robertolofaro/articles-model:Q4_K_M
Use Docker
docker model run hf.co/robertolofaro/articles-model:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use robertolofaro/articles-model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "robertolofaro/articles-model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "robertolofaro/articles-model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/robertolofaro/articles-model:Q4_K_M
- Ollama
How to use robertolofaro/articles-model with Ollama:
ollama run hf.co/robertolofaro/articles-model:Q4_K_M
- Unsloth Studio new
How to use robertolofaro/articles-model 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 robertolofaro/articles-model 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 robertolofaro/articles-model to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for robertolofaro/articles-model to start chatting
- Pi new
How to use robertolofaro/articles-model with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf robertolofaro/articles-model: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": "robertolofaro/articles-model:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use robertolofaro/articles-model with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf robertolofaro/articles-model: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 robertolofaro/articles-model:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use robertolofaro/articles-model with Docker Model Runner:
docker model run hf.co/robertolofaro/articles-model:Q4_K_M
- Lemonade
How to use robertolofaro/articles-model with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull robertolofaro/articles-model:Q4_K_M
Run and chat with the model
lemonade run user.articles-model-Q4_K_M
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -64,7 +64,10 @@ Given a natural language request such as:
|
|
| 64 |
|
| 65 |
the model returns a short answer structured as an executive summary followed by guidelines and hints.
|
| 66 |
|
| 67 |
-
As an example, with the request above, this is the answer that you could obtain from the [demo space](https://huggingface.co/spaces/robertolofaro/articles)
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
1. **Executive Summary:**
|
| 70 |
Italy is described as an "arrested development" where institutional and political structures are too weak to support change or innovation, often resulting in inefficiencies and a lack of coordination between levels of government. The potential lies not just in economic growth but also in cultural and social transformation through education, transparency, and shared leadership.
|
|
@@ -81,6 +84,27 @@ Italy is described as an "arrested development" where institutional and politica
|
|
| 81 |
- Regional diversity demands tailored solutions, not a "one-size-fits-all" approach to policy implementation.
|
| 82 |
- The role of the "middle class" as both driver and beneficiary of change is often overlooked in Italy’s political landscape.
|
| 83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
---
|
| 85 |
|
| 86 |
## About the articles
|
|
|
|
| 64 |
|
| 65 |
the model returns a short answer structured as an executive summary followed by guidelines and hints.
|
| 66 |
|
| 67 |
+
As an example, with the request above, this is the answer that you could obtain from the [demo space](https://huggingface.co/spaces/robertolofaro/articles),
|
| 68 |
+
as the demo is anyway set to be non-deterministic, you can get different answers each time:
|
| 69 |
+
|
| 70 |
+
#### Case 1
|
| 71 |
|
| 72 |
1. **Executive Summary:**
|
| 73 |
Italy is described as an "arrested development" where institutional and political structures are too weak to support change or innovation, often resulting in inefficiencies and a lack of coordination between levels of government. The potential lies not just in economic growth but also in cultural and social transformation through education, transparency, and shared leadership.
|
|
|
|
| 84 |
- Regional diversity demands tailored solutions, not a "one-size-fits-all" approach to policy implementation.
|
| 85 |
- The role of the "middle class" as both driver and beneficiary of change is often overlooked in Italy’s political landscape.
|
| 86 |
|
| 87 |
+
#### Case 2
|
| 88 |
+
|
| 89 |
+
1. **Executive Summary:**
|
| 90 |
+
Italy is described as a country with unique cultural and historical assets that are often underutilized due to structural barriers, lack of innovation, and outdated administrative practices. While it possesses rich resources in art, tourism, agriculture, and education, the potential remains largely unrealized unless systemic changes address inefficiencies, encourage foreign investment, and foster collaborative ecosystems between public and private sectors.
|
| 91 |
+
|
| 92 |
+
2. **Guidelines & Hints:**
|
| 93 |
+
- Italy's cultural heritage is a core asset but often limited by bureaucratic inertia and lack of strategic integration with modern economic needs (e.g., tourism focused on static consumption rather than dynamic experiences).
|
| 94 |
+
- Innovation and technology adoption are critical; the country suffers from "technological isolationism" where domestic companies avoid global expansion due to regulatory complexity.
|
| 95 |
+
- Foreign investment requires a shift toward transparent, collaborative partnerships rather than transactional relationships with local entities.
|
| 96 |
+
- Education must evolve from theory-focused models to practical skills aligned with market demands, including digital literacy and cross-cultural competencies for export-oriented roles.
|
| 97 |
+
- Administrative reform is essential—streamlining processes like tax incentives, construction permits, and regulatory frameworks to attract and retain talent and capital.
|
| 98 |
+
- Social cohesion and trust between citizens and institutions are foundational; without public confidence, structural reforms lack sustainable momentum.
|
| 99 |
+
- Export-focused strategies must leverage Italy’s manufacturing excellence while adapting for global markets through localized production and digital transformation.
|
| 100 |
+
- Sustainability requires balancing industrial growth with environmental responsibility—e.g., energy efficiency in agriculture, circular economy principles in waste management.
|
| 101 |
+
- Digital infrastructure gaps (e.g., internet access, data standards) hinder innovation ecosystems and remote work opportunities.
|
| 102 |
+
- Cultural promotion beyond tourism should include soft-power initiatives that highlight Italy’s roles as a mediator of global ideas (science, art, philosophy).
|
| 103 |
+
|
| 104 |
+
Therefore, consider the "demo" just as a demo- if you want to use the model to brainstorm, I suggest that you download the model and create your own script.
|
| 105 |
+
|
| 106 |
+
You can actually look at an example of the system prompt below.
|
| 107 |
+
|
| 108 |
---
|
| 109 |
|
| 110 |
## About the articles
|