Hugging Face's logo

Ikala-allen
/
llama2_knowledge_v4.1

Text Generation
Transformers
llama
Generated from Trainer
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Community
llama2_knowledge_v4.1 / README.md
Ikala-allen's picture
Ikala-allen
Model save
4030468
preview code
|
raw
history blame contribute delete
1.47 kB
metadata
license: apache-2.0
base_model: ziqingyang/chinese-llama-2-7b
tags:
  - generated_from_trainer
model-index:
  - name: llama2_knowledge_v4.1
    results: []

Built with Axolotl

llama2_knowledge_v4.1

This model is a fine-tuned version of ziqingyang/chinese-llama-2-7b on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 6
  • eval_batch_size: 6
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 5
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 120
  • total_eval_batch_size: 30
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 7

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1