metadata
base_model: safe049/SmolTuring-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- dpo
license: apache-2.0
language:
- en
HumanTuring-DPO-8B-Instruct
- Developed by: safe049
- License: apache-2.0
- Finetuned from model : safe049/SmolTuring-8B-Instruct
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Informations
Thanks for 1k downloads!
This model is trained by my smolturing model [which is a smollumi model trained with turing test dataset] with this dataset:
HumanLLMs/Human-Like-DPO-Dataset
Trained by unsloth in Google Colab