You can deploy this model and start earning money today!

thomasbllx/
ppo-ltr-run_approxndcg_seed123

Name: ppo-ltr-run_approxndcg_seed123
Availability: InStock

ppo-learning-to-rank

safetensors

model_hub_mixin

pytorch_model_hub_mixin

reward-model

text-ranking

8-bit

Views

No views yet

LLM judge reward model

This Llama 3 reward-model checkpoint is packaged with PyTorchModelHubMixin. Access to the gated meta-llama/Meta-Llama-3-8B-Instruct base model is required.

Usage

Install the dependencies and clone Tankiit/PPO_Learning_to_rank, then run on a CUDA machine:

python

from llm_judge_listnet_finetune import LLMJudgeRewardModel

model = LLMJudgeRewardModel.from_pretrained(
    "thomasbllx/ppo-ltr-run_approxndcg_seed123",
    map_location="cuda",
)

The evaluation metrics are included for reproducibility.