This repo contains RiskAgent model finetuned from meta-llama/Llama-3.2-3B-Instruct model using risk prediction data. More detail can be found from the Github

The model was trained with the following hypermeters:

  • cutoff_len: 3096
  • num_train_epochs: 5
  • learning_rate: 1.0e-4
  • warnup_ratio: 0.1
  • batch_size: 32
  • finetuning_type: lora

Prior to utilizing our model, please ensure you have obtained the Llama licensing and access rights to the Llama model.

Downloads last month
10
Safetensors
Model size
3.21B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for jinge13288/RiskAgent-3B

Finetuned
(291)
this model
Quantizations
1 model