saha2026/TwinLlama-3.1-8B-DPO
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
f07a016a2b48a0b4c72f8fe3f8578c6a7e0c2c33
TwinLlama-3.1-8B-DPO/README.md
ModelHub XC f07a016a2b 初始化项目，由ModelHub XC社区提供模型 
Model: saha2026/TwinLlama-3.1-8B-DPO
Source: Original Platform
2026-05-05 08:13:37 +08:00

577 B
Raw Blame History

base_model, language, license, tags
base_model language license tags
saha2026/TwinLlama-3.1-8B
en
apache-2.0
text-generation-inference
transformers
unsloth
llama
trl
dpo

Uploaded model

  • Developed by: saha2026
  • License: apache-2.0
  • Finetuned from model : saha2026/TwinLlama-3.1-8B

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