Downloads · 30 days
13
30% of all-time downloads
yejin-korean-3b-v25-sft-step14k
cooler8/yejin-korean-3b-v25-sft-step14k
yejin-korean-3b-v25-sft-step14k is a machine learning model from cooler8. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
A Korean-English bilingual instruction-following model with 3 billion parameters.
All-time downloads
43
Public
Parameters
3B
6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026
- SHA
- b138cada
Model card
From the Hugging Face model README
Yejin Korean 3B v2.5 SFT (Step 14K)
A Korean-English bilingual instruction-following model with 3 billion parameters.
Model Details
- Base Model: Yejin Korean 3B v2.5 Base (pre-trained + annealed)
- Parameters: 3B
- Languages: Korean, English
- Context Length: 4096 tokens
- Training: Supervised Fine-Tuning on high-quality Korean instruction data
- SFT Steps: 14,000 (partial training, Loss: 1.58)
- Precision: BF16
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("cooler8/yejin-korean-3b-v25-sft-step14k")
model = AutoModelForCausalLM.from_pretrained("cooler8/yejin-korean-3b-v25-sft-step14k", torch_dtype="auto")
prompt = "### 질문:\n대한민국의 수도는 어디인가요?\n\n### 답변:\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
License
Apache 2.0
- Type
- llama
- License
- apache-2.0
- Languages
- ko, en
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026