Downloads · 30 days
0
Jnx03/kanitakorn-qwen3-8b-sft-v5
kanitakorn-qwen3-8b-sft-v5 is a text generation model from Jnx03. Use it when you need the model to write or continue text. The card lists the license as odc-by.
A LoRA adapter on top of Qwen/Qwen3-8B, fifth iteration. Beats Pathumma-1.0-7B on 3 of 4 NLU benchmarks (Pathumma's published suite).
Downloads · 30 days
0
Access
Public
Updated May 18, 2026
Repo size
710 MB
Likes
0
Public
Click a slice to open those files.
.safetensors698 MB · 98%
From the Hugging Face model README
A LoRA adapter on top of Qwen/Qwen3-8B, fifth iteration. Beats Pathumma-1.0-7B on 3 of 4 NLU benchmarks (Pathumma's published suite).
| benchmark | Kanitakorn-v5 | Kanitakorn-v1 | Pathumma-1.0-7B (pub) | OpenThaiGPT-1.5-7B (pub) | result |
|---|---|---|---|---|---|
| xcopa_th | 0.867 | 0.833 | 0.83 | 0.854 | WIN +3.7pp |
| belebele_th | 0.833 | 0.767 | 0.7777 | 0.7944 | WIN +5.5pp |
| xnli_th | 0.633 | 0.20 | 0.4011 | 0.397 | WIN +23.2pp 🔥 |
| wisesight | 0.10 | 0.30 | 0.4129 | 0.5024 | regresses |
| benchmark | v5 (no /no_think) |
|---|---|
| ThaiExam (n=33 spot-check) | 0.424 |
| OpenThaiEval MCQ | 0.333 |
| IFEval-TH strict | 0.733 |
| MT-Bench-TH | 5.20 |
| MATH500-TH | 0.40 |
| HotpotQA EM | 0.200 |
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen3-8B"
adapter = "Jnx03/kanitakorn-qwen3-8b-sft-v5"
tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, adapter).merge_and_unload()
# IMPORTANT: do NOT inject /no_think for this SFT model.
# /no_think is for the raw Qwen3-8B base only.
# Let v5 reason naturally on Thai academic questions.
Qwen3-8B raw is already very strong on Thai NLU — our re-measurement shows raw beats Pathumma on belebele (0.933 vs 0.7777). v5's wins on xcopa/belebele are partly explained by the strong base; the xnli +23pp win IS the SFT's contribution.
wisesight regression (-20pp from v1): v5's training has Wildchat + Capybara English chat that may bias toward "positive" sentiment outputs. R6 (more wisesight + Thaweewat QA) addresses this.
ThaiExam regression (-7.9pp from v1): diversity-vs-specialization trade-off. v1 is more concentrated on Thai academic; v5 sacrifices some academic for broader NLU.
See https://huggingface.co/datasets/Jnx03/kanitakorn-th-sft for full development log and methodology.