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
```

iolai26-solve / script.py

Commit History

final submission

a1bdb40

rvpant commited on 30 days ago

Batch-1 no-padding generation; blend label-aware and positional answer alignment in lean

213ed63

rvpant commited on 30 days ago

Trim code comments to be concise and neutral

09e9927

rvpant commited on 30 days ago

Switch LLM pass to the minimal-prompt (lean) path by default

d4ab768

rvpant commited on 30 days ago

Add toggle to disable match_letters assignment pass (default off) for isolation

b32ea24

rvpant commited on about 1 month ago

Refine solver: greedy decoding config, lightweight linguistic-reasoning prompt, letter-matching via assignment, default device placement

5a28824

rvpant commited on about 1 month ago

Swap weights to Qwen2.5-14B-Instruct-AWQ (shard 3 + metadata)

42c1db7

rvpant commited on Jul 25

Add SYMBOLIC_ONLY toggle; enable it for a symbolic-baseline diagnostic submission

6737f54

rvpant commited on Jul 25

Fix output parsing that zeroed the score: tolerant markers, no prose fallback, salvage pass, adaptive modes

589b6aa

rvpant commited on Jul 25

Fix sandbox OOM: token-budget batching, OOM retry/abstain, checkpointed submission writes

e674d6d

rvpant commited on Jul 24

Ship Qwen2.5-7B-Instruct-AWQ weights at repo root (MODEL_ID='.')

f6c1260

rvpant commited on Jul 24

Notebook-style MODEL_ID in script.py; move metrics into solver/; untrack dev-only eval/tests/data

f96c703

rvpant commited on Jul 24

Single-shot-with-tools v1: scaffolded prompts, shared pipeline, explanation track

fc85791

rvpant commited on Jul 22

Initial commit: IOL-AI 2026 solver

379f378

rvpant commited on Jul 21

Commit History

final submission a1bdb40

Batch-1 no-padding generation; blend label-aware and positional answer alignment in lean 213ed63

Trim code comments to be concise and neutral 09e9927

Switch LLM pass to the minimal-prompt (lean) path by default d4ab768

Add toggle to disable match_letters assignment pass (default off) for isolation b32ea24

Refine solver: greedy decoding config, lightweight linguistic-reasoning prompt, letter-matching via assignment, default device placement 5a28824

Swap weights to Qwen2.5-14B-Instruct-AWQ (shard 3 + metadata) 42c1db7

Add SYMBOLIC_ONLY toggle; enable it for a symbolic-baseline diagnostic submission 6737f54

Fix output parsing that zeroed the score: tolerant markers, no prose fallback, salvage pass, adaptive modes 589b6aa

Fix sandbox OOM: token-budget batching, OOM retry/abstain, checkpointed submission writes e674d6d

Ship Qwen2.5-7B-Instruct-AWQ weights at repo root (MODEL_ID='.') f6c1260

Notebook-style MODEL_ID in script.py; move metrics into solver/; untrack dev-only eval/tests/data f96c703

Single-shot-with-tools v1: scaffolded prompts, shared pipeline, explanation track fc85791

Initial commit: IOL-AI 2026 solver 379f378

final submission

a1bdb40

Batch-1 no-padding generation; blend label-aware and positional answer alignment in lean

213ed63

Trim code comments to be concise and neutral

09e9927

Switch LLM pass to the minimal-prompt (lean) path by default

d4ab768

Add toggle to disable match_letters assignment pass (default off) for isolation

b32ea24

Refine solver: greedy decoding config, lightweight linguistic-reasoning prompt, letter-matching via assignment, default device placement

5a28824

Swap weights to Qwen2.5-14B-Instruct-AWQ (shard 3 + metadata)

42c1db7

Add SYMBOLIC_ONLY toggle; enable it for a symbolic-baseline diagnostic submission

6737f54

Fix output parsing that zeroed the score: tolerant markers, no prose fallback, salvage pass, adaptive modes

589b6aa

Fix sandbox OOM: token-budget batching, OOM retry/abstain, checkpointed submission writes

e674d6d

Ship Qwen2.5-7B-Instruct-AWQ weights at repo root (MODEL_ID='.')

f6c1260

Notebook-style MODEL_ID in script.py; move metrics into solver/; untrack dev-only eval/tests/data

f96c703

Single-shot-with-tools v1: scaffolded prompts, shared pipeline, explanation track

fc85791

Initial commit: IOL-AI 2026 solver

379f378