---
library_name: peft
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
license: apache-2.0
tags:
- thai
- kanitakorn
- single-model
- greedy-eval
language:
- th
- en
---

# Jnx03/kanitakorn-v58-format-null-guard-step1

Kanitakorn 2026-06-13 campaign artifact.

- Base: `deepseek-ai/DeepSeek-R1-Distill-Qwen-14B`
- Version: `v58-format-null-guard-step1`
- Method: `sft-lora`
- Final-claim policy: one model, no BoN, no self-consistency, no ensemble, no model routing.
- Date: 2026-06-15

## Scores

| Benchmark | Score | Target | Status |
|---|---:|---:|---|
| aime24_th | pending | >15.0 | pending |
| aime24 | pending | >25.0 | pending |
| math500_th | pending | >56.0 | pending |
| math500 | pending | >82.0 | pending |
| livecodebench_th | pending | >35.0 | pending |
| livecodebench | pending | >60.0 | pending |
| openthaieval | pending | >80.0 | pending |
| hotpotqa_th_en | pending | >46.0 | pending |
| instruction_following_th_en | pending | >57.0 | pending |
| mt_bench_th_en | pending | >85.0 | pending |
| thaiexam | pending | >70.0 | pending |
| ifeval_th | pending | >82.0 | pending |

## Notes

Automatic checkpoint publish from runs/20260615_deepseek_v58_format_null_guard_from_best_lr8e9_1/checkpoint-1. Single-model artifact; no BoN/self-consistency.