Edit model card

llama-3-8b-chat-patent-small

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the english translation of a small dataset of 16,000 Korean patents.

Model description

This model is provided for testing purposes only.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
16
Safetensors
Model size
8.03B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kimhyeongjun/llama-3-8b-patent-small-dataset

Finetuned
(441)
this model