Downloads · 30 days
0
kanana-1.5-8b-rlhf
jinn33/kanana-1.5-8b-rlhf
kanana-1.5-8b-rlhf is a machine learning model from jinn33. 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.
PPO (Proximal Policy Optimization)로 학습된 한국어 모델입니다.
Access
Public
Updated Jan 21, 2026
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.1 GB · 60%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026
- SHA
- a6ee31ab
Base models
Model card
From the Hugging Face model README
kanana-1.5-8b-rlhf
PPO (Proximal Policy Optimization)로 학습된 한국어 모델입니다.
학습 정보
- Base Model: Kanana 1.5 8B
- 학습 방법: PPO (RLHF)
- Batch Size: 80
- Learning Rate: 1e-5
사용 방법
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("jinn33/kanana-1.5-8b-rlhf")
model = AutoModelForCausalLM.from_pretrained("jinn33/kanana-1.5-8b-rlhf")
prompt = "### 질문: 안녕하세요\n\n### 답변:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))
- License
- apache-2.0
- Languages
- ko
- Created
- Jan 21, 2026
- Updated
- Jan 21, 2026