metadata
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- dpo
base_model: thewordsmiths/Meta-Llama-3-8B_sft_merged_100000
Uploaded model
- Developed by: thewordsmiths
- License: apache-2.0
- Finetuned from model : thewordsmiths/Meta-Llama-3-8B_sft_merged_100000
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.