koutch/short_paper_llama_2.json_train_dpo_v1_train_no_think
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Jan 14, 2026License:apache-2.0Architecture:Transformer Open Weights Cold
The koutch/short_paper_llama_2.json_train_dpo_v1_train_no_think model is an 8 billion parameter Llama 3.1 instruction-tuned language model developed by koutch. It was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is designed for general language generation tasks, leveraging its efficient training methodology.
Loading preview...