TheBloke
/

Llama-2-13B-fp16

Text Generation

text-generation-inference

Model card Files Files and versions Community

TheBloke commited on Jul 19, 2023

Commit

a862856

•

1 Parent(s): cf75555

Update README.md

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -33,11 +33,9 @@ They were produced by downloading the PTH files from Meta, and then converting t
 Command to convert was:
 ```
- python3 /workspace/venv/pytorch2/lib/python3.10/site-packages/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir /workspace/git/llama/download --model_size 13B --output_dir /workspace/process/llama-2-13b/source --safe_serialization true
 ```
-The files were saved in Safetensors format.
 ## Repositories available
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ)

 Command to convert was:
 ```
+ python3 /workspace/venv/pytorch2/lib/python3.10/site-packages/transformers/models/llama/convert_llama_weights_to_hf.py --input_dir /workspace/git/llama/download --model_size 13B --output_dir /workspace/process/llama-2-13b/source
 ```
 ## Repositories available
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Llama-2-13B-GPTQ)