text-generation-webui/requirements.txt

accelerate==0.17.0
bitsandbytes==0.37.0
flexgen==0.1.7
gradio==3.18.0
numpy
requests
rwkv==0.3.1
safetensors==0.3.0
sentencepiece
tqdm
git+https://github.com/zphang/transformers@llama_push
Bump accelerate, RWKV and safetensors 2023-03-12 18:25:14 +01:00			`accelerate==0.17.0`
Bump bitsandbytes version 2023-02-03 13:29:31 +01:00			`bitsandbytes==0.37.0`
Bump flexgen version 2023-03-02 16:03:57 +01:00			`flexgen==0.1.7`
Downgrade gradio version (file uploads are broken in 3.19.1) 2023-02-26 02:59:02 +01:00			`gradio==3.18.0`
Add softprompt support (for real this time) Is this too much voodoo for our purposes? 2023-02-13 19:25:16 +01:00			`numpy`
Add requests to requirements.txt 2023-03-11 18:47:30 +01:00			`requests`
Bump accelerate, RWKV and safetensors 2023-03-12 18:25:14 +01:00			`rwkv==0.3.1`
			`safetensors==0.3.0`
Add sentencepiece 2023-03-05 14:02:24 +01:00			`sentencepiece`
Add tqdm to requirements.txt 2023-03-12 12:48:16 +01:00			`tqdm`
Use new LLaMA implementation (this will break stuff. I am sorry) https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model 2023-03-09 21:59:15 +01:00			`git+https://github.com/zphang/transformers@llama_push`