Instructions to use rpant/iolai26-solve with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rpant/iolai26-solve with Transformers:

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

pipe = pipeline("text-generation", model="rpant/iolai26-solve")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rpant/iolai26-solve")
model = AutoModelForCausalLM.from_pretrained("rpant/iolai26-solve", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rpant/iolai26-solve with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rpant/iolai26-solve"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rpant/iolai26-solve",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rpant/iolai26-solve

SGLang

How to use rpant/iolai26-solve 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 "rpant/iolai26-solve" \
    --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": "rpant/iolai26-solve",
		"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 "rpant/iolai26-solve" \
        --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": "rpant/iolai26-solve",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rpant/iolai26-solve with Docker Model Runner:
```
docker model run hf.co/rpant/iolai26-solve
```

IOL-AI 2026 Solver

Solves IOL-style linguistics puzzles (Linguini CSV) with a single-shot LLM. Ships Qwen/Qwen2.5-14B-Instruct-AWQ (4-bit AWQ, Apache-2.0) at the repo root, loaded from MODEL_ID = "."; runs on a T4 within the 30-minute budget.

Architecture

script.py — entrypoint: reads /tmp/data/test.csv, writes submission.csv (id, pred JSON list, explanation). Config flags at the top; submission written before the model loads and after every step.
solver/pipeline.py — orchestration. The model answers every puzzle from a minimal prompt (no scaffold, no chain-of-thought); output is parsed into one answer per item and aligned by position. A light greedy-anchored self-consistency vote refines answers while the clock allows. A deterministic symbolic layer (solver/) is a last-resort fallback only.
solver/llm.py — batched transformers/AWQ generation, greedy, repetition_penalty=1.0, per-token deadline.
solver/direct.py — prompt and answer parsing.

Run

python3 script.py [test.csv] [submission.csv]   # defaults: /tmp/data/test.csv, submission.csv

Weights are the unmodified Qwen/Qwen2.5-14B-Instruct-AWQ release (Apache-2.0; LICENSE retained).

Downloads last month: 204

Safetensors

Model size

15B params

Tensor type

I32

F16

Model tree for rpant/iolai26-solve

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Quantized

Qwen/Qwen2.5-14B-Instruct-AWQ

Quantized

(4)

this model