Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
chahyunmook
/
kanana-1.5-8b-instruct-2505-r64-lora
like
0
Text Generation
PEFT
Safetensors
Transformers
jiwon9703/ko-hallucination-sft-v1
Korean
lora
sft
trl
unsloth
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
PEFT 0.18.0
This kanana model was trained 2x faster with
Unsloth
and Huggingface's TRL library.
Downloads last month
1
Inference Providers
NEW
Text Generation
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for
chahyunmook/kanana-1.5-8b-instruct-2505-r64-lora
Base model
kakaocorp/kanana-1.5-8b-instruct-2505
Adapter
(
32
)
this model
Dataset used to train
chahyunmook/kanana-1.5-8b-instruct-2505-r64-lora
jiwon9703/ko-hallucination-sft-v1
Viewer
•
Updated
Nov 20, 2025
•
48.7k
•
4
•
1