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
Delete qa_markdown_chroma_externalized.py
Browse files
qa_markdown_chroma_externalized.py
DELETED
|
@@ -1,55 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env python3
|
| 2 |
-
from qa_common import parse_args, build_prompt, generate_answer, save_result
|
| 3 |
-
# REVISED: Imported from the dedicated langchain_chroma package
|
| 4 |
-
from langchain_chroma import Chroma
|
| 5 |
-
from langchain_huggingface import HuggingFaceEmbeddings
|
| 6 |
-
from llama_cpp import Llama
|
| 7 |
-
|
| 8 |
-
# ====================== CHROMA SPECIFIC ======================
|
| 9 |
-
VECTORSTORE_PATH = "chroma_db"
|
| 10 |
-
MODEL_PATH = "articles-Q4_K_M.gguf"
|
| 11 |
-
|
| 12 |
-
print("Loading embedding model...")
|
| 13 |
-
embeddings = HuggingFaceEmbeddings(
|
| 14 |
-
model_name="BAAI/bge-small-en-v1.5",
|
| 15 |
-
encode_kwargs={'normalize_embeddings': True}
|
| 16 |
-
)
|
| 17 |
-
|
| 18 |
-
print("Loading Chroma vector store...")
|
| 19 |
-
vectorstore = Chroma(
|
| 20 |
-
persist_directory=VECTORSTORE_PATH,
|
| 21 |
-
embedding_function=embeddings
|
| 22 |
-
)
|
| 23 |
-
|
| 24 |
-
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
|
| 25 |
-
|
| 26 |
-
print("Loading LLM...")
|
| 27 |
-
llm = Llama(
|
| 28 |
-
model_path=MODEL_PATH,
|
| 29 |
-
n_ctx=65000,
|
| 30 |
-
n_threads=8,
|
| 31 |
-
verbose=False,
|
| 32 |
-
)
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
def get_context(query: str) -> str:
|
| 36 |
-
"""Retrieve context using Chroma"""
|
| 37 |
-
docs = retriever.invoke(query)
|
| 38 |
-
return "\n\n".join([
|
| 39 |
-
f"[Article: {doc.metadata.get('article_title', 'N/A')}] "
|
| 40 |
-
f"{doc.page_content}"
|
| 41 |
-
for doc in docs
|
| 42 |
-
])
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
if __name__ == "__main__":
|
| 46 |
-
args = parse_args()
|
| 47 |
-
query = args.prompt if args.prompt else input("\nQuestion: ")
|
| 48 |
-
|
| 49 |
-
print("Retrieving context and generating answer...\n")
|
| 50 |
-
|
| 51 |
-
context = get_context(query)
|
| 52 |
-
prompt = build_prompt(query, context)
|
| 53 |
-
answer = generate_answer(llm, prompt)
|
| 54 |
-
|
| 55 |
-
save_result(query, answer, args.output)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|