kihyun-K/kanana-1.5-8b-instruct-2505-Safe-DPO
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
040e511f2294637afaa3eb6303df6b03ccd82c88
kanana-1.5-8b-instruct-2505…/README.md
ModelHub XC 040e511f22 初始化项目，由ModelHub XC社区提供模型 
Model: kihyun-K/kanana-1.5-8b-instruct-2505-Safe-DPO
Source: Original Platform
2026-10-22 16:19:17 +08:00

615 B
Raw Blame History

base_model, tags, license, language
base_model tags license language
kihyun-K/kanana-1.5-8b-instruct-2505-Safe-DPO
text-generation-inference
transformers
unsloth
llama
apache-2.0
en

Uploaded finetuned model

  • Developed by: kihyun-K
  • License: apache-2.0
  • Finetuned from model : kihyun-K/kanana-1.5-8b-instruct-2505-Safe-DPO

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.