⚽ Football Coaching LLM — Qwen2 7B (DPO v2)

A holistic football coaching assistant fine-tuned on Qwen2-7B using supervised fine-tuning (SFT) + Constitutional AI preference learning (DPO). Built on a RAG knowledge base of ~500M tokens spanning 11 domains, 66 subthemes, and 460+ football concepts.


Developer	Dylan Johnson — Finta Sports
Organization	Finta / FintaLab
Base Model	`unsloth/qwen2-7b-bnb-4bit` (Qwen2 7B)
Fine-tuning	QLoRA (SFT) + DPO with Constitutional AI
Training Data	~13,000 football coaching examples + 560 CAI preference pairs
RAG Corpus	~500M tokens · 11 domains · 66 subthemes · 460+ concepts
Knowledge Map	llm.fintalab.com/knowledge_map
RAG Knowledge Base	NotebookLM — Football RAG
Ecosystem	fintalab.com

Available Models

This repository contains multiple model formats to suit different deployment scenarios:

File	Format	Size	Use Case
`adapter_model.safetensors`	LoRA adapter (PEFT)	323 MB	Load on top of `unsloth/qwen2-7b-bnb-4bit` via Transformers + PEFT. Best for fine-tuning workflows and GPU inference.
`qwen2-7b.Q3_K_M.gguf`	GGUF Q3_K_M	3.81 GB	3-bit quantized model. Smallest footprint — runs on very limited hardware (6 GB RAM). Some quality loss vs Q4.
`qwen2-7b.Q4_K_M.gguf`	GGUF Q4_K_M	4.68 GB	4-bit quantized model. Ideal for local inference via llama.cpp, Ollama, LM Studio. Best balance of speed and quality.
`qwen2-7b.F16.gguf`	GGUF F16	15.2 GB	Full 16-bit precision model. Maximum quality, requires more VRAM/RAM.

Model Details

Property	Value
Base model	`unsloth/qwen2-7b-bnb-4bit`
Architecture	Qwen2 7B (8B params)
Fine-tuning method	QLoRA (SFT) + DPO
LoRA rank	32
LoRA alpha	64
Target modules	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Training data	~13,000 football coaching examples
SFT epochs	3
DPO epochs	1 (560 CAI preference pairs)
Quantization	4-bit (NF4)

Capabilities

Session planning & drill design — Generate structured training sessions across all age groups (U8 to Senior), with progressions, coaching points, and time breakdowns.
Tactical analysis — Formations, pressing structures, build-up play, transition patterns, and set-piece strategies grounded in the RAG knowledge base.
Periodization — Season planning, mesocycle/microcycle structuring, and load management frameworks.
Player development — Age-appropriate coaching pathways, individual development plans, and talent identification principles.
Coaching cues & feedback — Specific verbal and visual cues for technique correction and tactical communication.
Holistic coaching methodology — Integrates tactical, physical, mental, and social dimensions of player development.

Usage

Option 1: LoRA Adapter (Transformers + PEFT)

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch

base_model = "unsloth/qwen2-7b-bnb-4bit"
adapter_path = "Fintacorp55/football-llm-q4"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(adapter_path)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    quantization_config=bnb_config,
    device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter_path)

messages = [{"role": "user", "content": "Design a pressing drill for U16 players."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Option 2: GGUF via llama.cpp (Python)

from llama_cpp import Llama

llm = Llama(
    model_path="./football-llm-q4_K_M.gguf",
    n_ctx=4096,
    n_threads=8,
    n_gpu_layers=35  # Adjust for your hardware; set to 0 for CPU-only
)

output = llm(
    "Explain the principles of positional play in a 4-3-3 formation.",
    max_tokens=512,
    temperature=0.7,
)
print(output["choices"][0]["text"])

Option 3: Ollama

# Import the GGUF directly
ollama create football-coach -f Modelfile
ollama run football-coach

Option 4: LM Studio

Download football-llm-q4_K_M.gguf (4.68 GB) or football-llm-q4-f16.gguf (15.2 GB) and load directly in LM Studio.

Training Pipeline

RAG Knowledge Base (~500M tokens)
        │
        ▼
┌─────────────────────┐
│  1. Data Cleaning    │  10,000 filtered examples from RAG corpus
└────────┬────────────┘
         │
         ▼
┌─────────────────────┐
│  2. Synthetic QA     │  3,002 Claude-generated football Q&A pairs
└────────┬────────────┘
         │
         ▼
┌─────────────────────┐
│  3. SFT v2           │  Fine-tuned on 13,002 merged examples
│                       │  3 epochs · LoRA rank 32 · alpha 64
└────────┬────────────┘
         │
         ▼
┌─────────────────────┐
│  4. CAI Pairs         │  560 Constitutional AI preference pairs
│                       │  Generated via Claude API
└────────┬────────────┘
         │
         ▼
┌─────────────────────┐
│  5. DPO v2            │  Preference learning · beta=0.1
│                       │  Reward accuracy: 100%
└────────┬────────────┘
         │
         ▼
┌─────────────────────┐
│  6. GGUF Export       │  Q4_K_M (4.68 GB) + F16 (15.2 GB)
│                       │  Merged LoRA → full model → quantized
└─────────────────────┘

Data Sources

The RAG knowledge base that produced the training data draws from three pillars:

FBref Analytics — Player and team advanced metrics (xG, xA, progressive actions, defensive stats) across the European Big 5 leagues.
Cocoon Tactical Articles — In-depth tactical analysis: formations, pressing systems, transition play, positional structures, coaching methodologies.
Curated Football Corpus — Coaching manuals, periodization frameworks, player development literature, and match analysis content.

Knowledge Map

The underlying RAG structure is visualized as an interactive mindmap at llm.fintalab.com/knowledge_map:

11 Domains — High-level categories spanning the full football intelligence landscape.
66 Subthemes — Granular topic areas within each domain.
460+ Concepts — Specific knowledge nodes extracted from the RAG corpus.
Council Agent System — Select domain experts from the map to assemble a multi-agent "council." The system generates tailored prompts for focused, multi-perspective analysis.

You can also explore the RAG conversationally via the Football RAG on NotebookLM.

Part of the Finta Ecosystem

This model is one component of a broader sports intelligence platform at fintalab.com — a 12-instrument ecosystem that decomposes athletic performance into measurable dimensions (tactical, predictive, biomechanical, cognitive) across football, tennis, and general sports coaching. The LLM and Knowledge Map are instruments #11 and #12 in that toolkit.

Limitations

Domain scope — Optimized for football/soccer coaching contexts. Performance on non-football queries will default to the base Qwen2 model's capabilities.
Expert validation — Responses may require professional review for elite-level tactical or physical preparation decisions.
League coverage — FBref data skews toward the European Big 5 (Premier League, La Liga, Bundesliga, Serie A, Ligue 1). Lower divisions and non-European leagues have less coverage.
Knowledge cutoff — Based on training data collection date; no live or real-time match data.
Quantization trade-offs — Q4_K_M reduces size and improves speed at the cost of some precision vs. F16.
Language — Primarily English. Some French-language tactical content from Ligue 1/Ligue 2 sources.

Ethical Considerations

Intended for educational, analytical, and coaching purposes.
Should not be used for gambling, match manipulation, or sports integrity violations.
Player data sourced from publicly available statistics (FBref) and published analyses.
Users should exercise critical judgment when applying AI-generated coaching recommendations.

Citation

@misc{finta_football_llm_2025,
  title={Football Coaching LLM: A Domain-Specific Fine-Tuned Model with RAG Knowledge Base for Football Intelligence},
  author={Johnson, Dylan},
  year={2025},
  url={https://huggingface.co/Fintacorp55/football-llm-q4},
  note={Finta Sports / FintaLab}
}

Contact

Website — fintalab.com
LinkedIn — Dylan Johnson
Knowledge Map — llm.fintalab.com/knowledge_map
RAG Knowledge Base — NotebookLM

Questions, feedback, or collaboration ideas? Let's talk on LinkedIn.

Downloads last month: 346

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

3-bit

4-bit

16-bit