Hugging Face's logo

A2H0H0R1
/
llama2-7B-gpt4

Text Generation
Transformers
PyTorch
llama
llama-factory
lora
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
llama2-7B-gpt4 / README.md
A2H0H0R1's picture
A2H0H0R1
Update README.md
b0f8018
preview code
|
raw
history blame contribute delete
1.29 kB
metadata
license: other
base_model: NousResearch/Llama-2-7b-chat-hf
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: 2023-11-29-06-20-56
    results: []
datasets:
  - A2H0H0R1/alpaca_data_gpt4_2

2023-11-29-06-20-56

This model is a fine-tuned version of NousResearch/Llama-2-7b-chat-hf on the alpaca_data_gpt4_2 dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

https://huggingface.co/A2H0H0R1/llama2-7B-gpt4/blob/main/training_loss.png

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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

Training results

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.7
  • Tokenizers 0.14.1