RichardErkhov/kimhyeongjun_-_llama-3-8b-patent-small-dataset-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-8b-patent-small-dataset - GGUF

• —Model creator: https://huggingface.co/kimhyeongjun/
• —Original model: https://huggingface.co/kimhyeongjun/llama-3-8b-patent-small-dataset/

Original model description: --- license: other base_model: meta-llama/Meta-Llama-3-8B-Instruct tags:

• —llama-factory
• —full
• —generatedfromtrainer model-index:
• —name: llama-3-8b-chat-patent-small results: [] language:
• —en ---

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
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —num_epochs: 3.0
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.39.3
• —Pytorch 2.1.1+cu121
• —Datasets 2.18.0
• —Tokenizers 0.15.2