Instructions to use Alogotron/GameTheory-Solver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alogotron/GameTheory-Solver with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "Alogotron/GameTheory-Solver")

Transformers

How to use Alogotron/GameTheory-Solver with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Alogotron/GameTheory-Solver")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Alogotron/GameTheory-Solver", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Alogotron/GameTheory-Solver with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Alogotron/GameTheory-Solver

SGLang

How to use Alogotron/GameTheory-Solver with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Alogotron/GameTheory-Solver" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alogotron/GameTheory-Solver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Alogotron/GameTheory-Solver" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alogotron/GameTheory-Solver",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Alogotron/GameTheory-Solver with Docker Model Runner:
```
docker model run hf.co/Alogotron/GameTheory-Solver
```

Alogotron commited on Jun 5

Commit

0b7230e

verified ·

1 Parent(s): f90e9ec

Add Related Work (IJCAI survey, DeepMind SHOR-PSRO) and BibTeX citation

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -252,6 +252,30 @@ print(response)
 ---
 ## 📄 License
 This adapter is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).

 ---
+---
+## 📚 Related Work
+- **"Game Theory Meets Large Language Models: A Systematic Survey"** — IJCAI 2025 ([arxiv:2502.09053](https://arxiv.org/abs/2502.09053)) — The definitive survey on game theory × LLMs, covering RLHF alignment, multi-agent interactions, and strategic reasoning.
+- **DeepMind SHOR-PSRO** (April 2026) — LLM-driven rewriting of game theory algorithms that outperformed hand-designed baselines ([MarkTechPost](https://www.marktechpost.com/2026/04/03/google-deepminds-research-lets-an-llm-rewrite-its-own-game-theory-algorithms-and-it-outperformed-the-experts/)).
+- **GT-HarmBench** — Game-theoretic framing for AI safety benchmarking ([arxiv:2602.12316](https://arxiv.org/abs/2602.12316)).
+## 📄 Citation
+```bibtex
+@model{alogotron_gametheory_solver_2026,
+  author    = {Alogotron},
+  title     = {GameTheory-Solver: QLoRA Fine-Tuned Game Theory Problem Solver},
+  year      = {2026},
+  publisher = {Hugging Face},
+  url       = {https://huggingface.co/Alogotron/GameTheory-Solver},
+  note      = {Phase 1 SFT adapter achieving 94\% accuracy on GameTheory-Bench}
+}
+```
 ## 📄 License
 This adapter is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).