Uploaded finetuned model

  • Developed by: DuongTrongChi
  • License: apache-2.0
  • Finetuned from model : DuongTrongChi/Sailor-1.8b-chat-sft-v1

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
32
Safetensors
Model size
1.84B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DuongTrongChi/sailor-dpo

Base model

Qwen/Qwen1.5-1.8B
Finetuned
sail/Sailor-1.8B
Finetuned
(2)
this model

Collection including DuongTrongChi/sailor-dpo