Instructions to use jithinjames/iol-ai-2026-solver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use jithinjames/iol-ai-2026-solver with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jithinjames/iol-ai-2026-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": "jithinjames/iol-ai-2026-solver", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/jithinjames/iol-ai-2026-solver
- SGLang
How to use jithinjames/iol-ai-2026-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 "jithinjames/iol-ai-2026-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": "jithinjames/iol-ai-2026-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 "jithinjames/iol-ai-2026-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": "jithinjames/iol-ai-2026-solver", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use jithinjames/iol-ai-2026-solver with Docker Model Runner:
docker model run hf.co/jithinjames/iol-ai-2026-solver
Relax FINAL ANSWERS marker regex -- was silently failing to match if model put an answer on the same line as the marker
Browse files
script.py
CHANGED
|
@@ -79,7 +79,7 @@ def parse_answers(text, expected_count=None):
|
|
| 79 |
If expected_count is given, pad with "" or truncate so the row never silently
|
| 80 |
drops points from a length mismatch against the scorer's positional alignment.
|
| 81 |
"""
|
| 82 |
-
marker = list(re.finditer(r"(?im)^[#*\s]*final answers?[:#*\s]*
|
| 83 |
if marker:
|
| 84 |
text = text[marker[-1].end():]
|
| 85 |
answers = []
|
|
|
|
| 79 |
If expected_count is given, pad with "" or truncate so the row never silently
|
| 80 |
drops points from a length mismatch against the scorer's positional alignment.
|
| 81 |
"""
|
| 82 |
+
marker = list(re.finditer(r"(?im)^[#*\s]*final answers?[:#*\s]*", text))
|
| 83 |
if marker:
|
| 84 |
text = text[marker[-1].end():]
|
| 85 |
answers = []
|