Model Card

Model Details

  • Base Model: Qwen/Qwen2.5-7B
  • Dataset: cloudwalk-kickass/lending_semantic-first_loan-injected
  • Dataset size: 29242
  • Generation Dataset: helene-rousset/lending_raw_r1_qwen_32b_distill_r1_lending

Training

This model was fine-tuned using the following hyperparameters:

  • Learning rate: 1e-05
  • Batch size: 4
  • Max epochs: 2
  • Weight decay: 0.01

Prompt

  • Prefix: You are tasked with analyzing structured credit reports and evaluating whether a merchant is likely to repay a future loan. Your goal is to evaluate the provided information and output a binary prediction: 'True' if the merchant is likely to repay the loan, or 'False' if the merchant is unlikely to repay. \ Please reason step by step, and put your final answer within \boxed{}:
Downloads last month
0
Safetensors
Model size
7.62B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.