Files
iolai26-solve/README.md
ModelHub XC 5b016c1af1 初始化项目,由ModelHub XC社区提供模型
Model: rpant/iolai26-solve
Source: Original Platform
2026-07-28 09:36:12 +08:00

42 lines
1.5 KiB
Markdown

---
license: apache-2.0
base_model: Qwen/Qwen2.5-14B-Instruct-AWQ
library_name: transformers
pipeline_tag: text-generation
language:
- en
tags:
- iol-ai-2026
- linguistic-reasoning
---
# 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
```bash
python3 script.py [test.csv] [submission.csv] # defaults: /tmp/data/test.csv, submission.csv
```
Weights are the unmodified
[Qwen/Qwen2.5-14B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-AWQ)
release (Apache-2.0; `LICENSE` retained).