metadata
license: mit
PairRanker used in llm-blender, trained on deberta-v3-large.
Usage Example
Since PairRanker contains some custom layers and tokens. We recommend use our pairranker with our llm-blender python repo.
Otherwise, loading it directly with hugging face from_pretrained() API will encounter errors.
First install llm-blender by pip install git+https://github.com/yuchenlin/LLM-Blender.git
Then use pairranker with the following code:
import llm_blender
# ranker config
ranker_config = llm_blender.RankerConfig()
ranker_config.ranker_type = "pairranker" # only supports pairranker now.
ranker_config.model_type = "deberta"
ranker_config.model_name = "microsoft/deberta-v3-large" # ranker backbone
ranker_config.load_checkpoint = "llm-blender/pair-ranker" # hugging face hub model path or your local ranker checkpoint <your checkpoint path>
ranker_config.cache_dir = "./hf_models" # hugging face model cache dir
ranker_config.source_maxlength = 128
ranker_config.candidate_maxlength = 128
ranker_config.n_tasks = 1 # number of singal that has been used to train the ranker. This checkpoint is trained using BARTScore only, thus being 1.
fuser_config = llm_blender.GenFuserConfig()
# ignore fuser config as we don't use it here. You can load it if you want
blender_config = llm_blender.BlenderConfig()
# blender config
blender_config.device = "cuda" # blender ranker and fuser device
blender = llm_blender.Blender(blender_config, ranker_config, fuser_config)
Then you are good to use pairrankers with
blender.rank()to rank candidatesblender.compare()to compare 2 candiates. See LLM-Blender Github README.md and jupyter file blender_usage.ipynb for detailed usage examples.