Downloads · 30 days
0
0% of all-time downloads
Chinese-Llama-2-LoRA-7B
seeledu/Chinese-Llama-2-LoRA-7B
Chinese-Llama-2-LoRA-7B is a machine learning model from seeledu. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
The LoRA version of Chinese-Llama-2 base on Llama-2-7b-hf.
All-time downloads
2
Public
Repo size
16.8 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin8.4 MB · 100%
At a glance
- Access
- Public
- Created
- Jul 21, 2023
- Updated
- Jul 21, 2023
- SHA
- d8007499
Model card
From the Hugging Face model README
Chinese-Llama-2-LoRA-7B
The LoRA version of Chinese-Llama-2 base on Llama-2-7b-hf.
The Github homepage is here:https://github.com/longyuewangdcu/Chinese-Llama-2/.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 1
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
How to Use
Download the lora model weight in your project path
python3 inference_lora.py --model-name-or-path <your_proj_path>/llama2-7b
--lora-weights <your_proj_path>/Chinese-Llama-2-LoRA-7B/adapter_model
-t 0.7
-sa 'sample'
-i test/test_case.txt
-o test/test_case.general-task.txt
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
- Created
- Jul 21, 2023
- Updated
- Jul 21, 2023