Instructions to use philippotiger/forecast-extractor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philippotiger/forecast-extractor with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="philippotiger/forecast-extractor",
	filename="football-extractor-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 philippotiger/forecast-extractor with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf philippotiger/forecast-extractor:F16
# Run inference directly in the terminal:
llama-cli -hf philippotiger/forecast-extractor:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf philippotiger/forecast-extractor:F16
# Run inference directly in the terminal:
llama-cli -hf philippotiger/forecast-extractor:F16

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 philippotiger/forecast-extractor:F16
# Run inference directly in the terminal:
./llama-cli -hf philippotiger/forecast-extractor:F16

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 philippotiger/forecast-extractor:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf philippotiger/forecast-extractor:F16

Use Docker

docker model run hf.co/philippotiger/forecast-extractor:F16

LM Studio
Jan

vLLM

How to use philippotiger/forecast-extractor with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/philippotiger/forecast-extractor:F16

Ollama
How to use philippotiger/forecast-extractor with Ollama:
```
ollama run hf.co/philippotiger/forecast-extractor:F16
```

Unsloth Studio new

How to use philippotiger/forecast-extractor 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 philippotiger/forecast-extractor 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 philippotiger/forecast-extractor to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for philippotiger/forecast-extractor to start chatting

Pi new

How to use philippotiger/forecast-extractor with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf philippotiger/forecast-extractor:F16

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": "philippotiger/forecast-extractor:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philippotiger/forecast-extractor with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf philippotiger/forecast-extractor:F16

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 philippotiger/forecast-extractor:F16

Run Hermes

hermes

Docker Model Runner
How to use philippotiger/forecast-extractor with Docker Model Runner:
```
docker model run hf.co/philippotiger/forecast-extractor:F16
```

Lemonade

How to use philippotiger/forecast-extractor with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull philippotiger/forecast-extractor:F16

Run and chat with the model

lemonade run user.forecast-extractor-F16

List all available models

lemonade list

forecast-extractor

A fine-tuned version of Qwen2.5-3B-Instruct for extracting structured JSON from football prediction messages (e.g. Telegram tip channels).

What it does

Given a raw football prediction message, it returns a structured JSON array:

[
  {
    "league": "La Liga",
    "team_1": "Real Madrid",
    "team_2": "Barcelona",
    "prediction": "1X",
    "date": "25/03/2026",
    "odds": 1.42
  }
]

Handles:

Single and multi-tip messages (up to 4 tips)
Bold unicode text (Telegram formatting)
Missing fields → null
Varied formats, emojis, noise

Models

File	Size	Description
`football-extractor-q4.gguf`	1.8GB	Q4_K_M quantized — recommended
`football-extractor-f16.gguf`	5.8GB	Full f16 precision

Quick start

With llama-cpp-python (recommended)

from llama_cpp import Llama
import json

llm = Llama(model_path="football-extractor-q4.gguf", n_ctx=2048, n_gpu_layers=-1)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "Extract structured data and return ONLY a valid JSON array. Keys: league, team_1, team_2, prediction, date, odds. Use null for missing fields."},
        {"role": "user", "content": "YOUR TIP TEXT HERE"}
    ],
    temperature=0.0,
    max_tokens=512,
)
print(json.loads(response["choices"][0]["message"]["content"]))

With Ollama

ollama pull philippotiger/forecast-extractor
ollama run philippotiger/forecast-extractor

Training details

Base model: Qwen/Qwen2.5-3B-Instruct
Method: QLoRA (4-bit NF4) with LoRA r=8
Dataset: 300 synthetic examples generated from real team data
- 70% single-tip, 30% multi-tip (2-4 events)
- 10 message templates with emoji injection, typos, missing fields
Epochs: 3
Final val loss: ~0.24

Intended use

Parsing football prediction messages from Telegram channels or similar sources into structured data for further processing or storage.

Downloads last month: 16

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

16-bit

View +1 variant

Model tree for philippotiger/forecast-extractor

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1265)

this model