Downloads · 30 days
4
17% of all-time downloads
Jnx03/kanitakorn-r1d-qwen14b-stage1-r1d-v7-mega-20260522
kanitakorn-r1d-qwen14b-stage1-r1d-v7-mega-20260522 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 mit.
LoRA adapter from the Kanitakorn 7-day Thai LLM campaign.
Downloads · 30 days
4
17% of all-time downloads
All-time downloads
24
Public
Repo size
80.3 MB
Likes
0
Public
Click a slice to open those files.
.safetensors68.9 MB · 86%
From the Hugging Face model README
LoRA adapter from the Kanitakorn 7-day Thai LLM campaign.
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B—{
"lr": 2e-06,
"r": 8,
"epochs": 0.7,
"qlora": true,
"data": "10918 unique Thai SFT (2x v6)",
"thai_weight": 0.45
}
| Benchmark | Score | Target | Beat? |
|---|---|---|---|
| — | — | — | — |
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
adapter = "Jnx03/kanitakorn-r1d-qwen14b-stage1-r1d-v7-mega-20260522"
tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto", trust_remote_code=True)
model = PeftModel.from_pretrained(model, adapter)
See VERSION_LOG.md for context on this checkpoint vs siblings.
License: MIT (inherited from deepseek-ai/DeepSeek-R1-Distill-Qwen-14B).