A newer version of the Gradio SDK is available:
4.42.0
LLaMA-v2
To convert LLaMA-v2 from the .pth
format provided by Meta to transformers format, follow the steps below:
cd
into yourllama
folder (the one containingdownload.sh
and the models that you downloaded):
cd llama
- Clone the transformers library:
git clone 'https://github.com/huggingface/transformers'
- Create symbolic links from the downloaded folders to names that the conversion script can recognize:
ln -s llama-2-7b 7B
ln -s llama-2-13b 13B
- Do the conversions:
mkdir llama-2-7b-hf llama-2-13b-hf
python ./transformers/src/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir . --model_size 7B --output_dir llama-2-7b-hf --safe_serialization true
python ./transformers/src/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir . --model_size 13B --output_dir llama-2-13b-hf --safe_serialization true
Move the output folders inside
text-generation-webui/models
Have fun