metadata
license: llama3
pipeline_tag: text-generation
base_model: Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-Concise-R
LLaMA-3-8B-SFR-Iterative-DPO-Concise-R-GGUF
This is quantized version of Salesforce/LLaMA-3-8B-SFR-Iterative-DPO-Concise-R created using llama.cpp
Model Description
This is a concise version of Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R. In the training, a concise penalty is applied.