Downloads · 30 days
5
20% of all-time downloads
kanitakorn-v30a-step8
Jnx03/kanitakorn-v30a-step8
kanitakorn-v30a-step8 is a machine learning model from Jnx03. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Kanitakorn 2026-06-13 campaign artifact.
All-time downloads
25
Public
Repo size
278 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors258 MB · 93%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Jun 14, 2026
- SHA
- 2c700735
Base models
Model card
From the Hugging Face model README
Jnx03/kanitakorn-v30a-step8
Kanitakorn 2026-06-13 campaign artifact.
- Base:
Qwen/Qwen3.5-9B - Version:
v30a-step8 - Method:
sft-lora - Final-claim policy: one model, no BoN, no self-consistency, no ensemble, no model routing.
- Date: 2026-06-14
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/20260614_qwen35_v30a_targeted_thaiexam_lr8e8_16/checkpoint-8. Single-model artifact; no BoN/self-consistency.
- Library
- peft
- License
- apache-2.0
- Languages
- th, en
- Created
- Jun 14, 2026
- Updated
- Jun 14, 2026