Downloads · 30 days
0
Jnx03/kanitakorn-qwen3-8b-sft-v7-simpo
kanitakorn-qwen3-8b-sft-v7-simpo 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.
R6 LoRA + APOzero preference optimization (SimPO-class loss) on 469 codex-distilled Thai preference pairs. Chat-quality polished variant.
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
R6 LoRA + APO_zero preference optimization (SimPO-class loss) on 469 codex-distilled Thai preference pairs. Chat-quality polished variant.
| benchmark | v7 | R6 | v1 | v5 |
|---|---|---|---|---|
| ThaiExam | 0.479 | 0.467 | 0.503 | 0.424 |
| IFEval-TH strict | 0.800 | 0.800 | 0.667 | 0.733 |
| MT-Bench-TH | 6.067 | 6.80 | 4.50 | 5.20 |
| MATH500-TH | 0.267 | 0.333 | 0.533 | 0.40 |
| OpenThaiEval MCQ | 0.333 | 0.333 | 0.267 | 0.333 |
| HotpotQA EM | 0.067 | 0.067 | 0.200 | 0.200 |
| benchmark | v7 | R6 | Pathumma-pub |
|---|---|---|---|
| xcopa_th | — | 0.833 | 0.83 |
| belebele_th | — | 0.867 | 0.7777 |
| xnli_th | — | 0.567 | 0.4011 |
| wisesight | — | 0.70 | 0.4129 |
DPOConfig(
loss_type="apo_zero", # Anchored preference optimization, reference-free
beta=2.5,
learning_rate=1e-6,
num_train_epochs=2,
per_device_train_batch_size=2, gradient_accumulation_steps=16,
max_length=2048, max_prompt_length=1800,
lr_scheduler_type="cosine", warmup_ratio=0.1,
)
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "Jnx03/kanitakorn-qwen3-8b-sft-v7-simpo").merge_and_unload()
# Same as R6 — do NOT inject /no_think for SFT models.