text-generation-webui/requirements.txt

accelerate==0.18.0
bitsandbytes==0.37.2
flexgen==0.1.7
gradio==3.24.0
llamacpp==0.1.11
markdown
numpy
peft==0.2.0
requests
rwkv==0.7.1
safetensors==0.3.0
sentencepiece
tqdm
datasets
git+https://github.com/huggingface/transformers
Bump accelerate from 0.17.1 to 0.18.0 Bumps [accelerate](https://github.com/huggingface/accelerate) from 0.17.1 to 0.18.0. - [Release notes](https://github.com/huggingface/accelerate/releases) - [Commits](https://github.com/huggingface/accelerate/compare/v0.17.1...v0.18.0) --- updated-dependencies: - dependency-name: accelerate dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com> 2023-03-27 21:19:34 -04:00			`accelerate==0.18.0`
Bump bitsandbytes from 0.37.1 to 0.37.2 Bumps [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) from 0.37.1 to 0.37.2. - [Release notes](https://github.com/TimDettmers/bitsandbytes/releases) - [Changelog](https://github.com/TimDettmers/bitsandbytes/blob/main/CHANGELOG.md) - [Commits](https://github.com/TimDettmers/bitsandbytes/commits) --- updated-dependencies: - dependency-name: bitsandbytes dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> 2023-03-27 17:05:19 -04:00			`bitsandbytes==0.37.2`
Bump flexgen version 2023-03-02 10:03:57 -05:00			`flexgen==0.1.7`
Bump gradio version (make sure to update) This fixes the textbox shrinking vertically once it reaches a certain number of lines. 2023-03-30 23:42:26 -04:00			`gradio==3.24.0`
Bump llamacpp version 2023-03-31 14:08:01 -04:00			`llamacpp==0.1.11`
Sort the requirements 2023-03-15 11:40:03 -04:00			`markdown`
Add softprompt support (for real this time) Is this too much voodoo for our purposes? 2023-02-13 13:25:16 -05:00			`numpy`
Add LoRA support 2023-03-16 20:31:39 -04:00			`peft==0.2.0`
Add requests to requirements.txt 2023-03-11 12:47:30 -05:00			`requests`
Bump rwkv from 0.7.0 to 0.7.1 Bumps [rwkv](https://github.com/BlinkDL/ChatRWKV) from 0.7.0 to 0.7.1. - [Release notes](https://github.com/BlinkDL/ChatRWKV/releases) - [Commits](https://github.com/BlinkDL/ChatRWKV/commits) --- updated-dependencies: - dependency-name: rwkv dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> 2023-03-27 17:05:35 -04:00			`rwkv==0.7.1`
Bump accelerate, RWKV and safetensors 2023-03-12 13:25:14 -04:00			`safetensors==0.3.0`
Add sentencepiece 2023-03-05 08:02:24 -05:00			`sentencepiece`
Add tqdm to requirements.txt 2023-03-12 07:48:16 -04:00			`tqdm`
initial lora training tab 2023-03-25 15:08:26 -04:00			`datasets`
The LLaMA PR has been merged into transformers https://github.com/huggingface/transformers/pull/21955 The tokenizer class has been changed from "LLaMATokenizer" to "LlamaTokenizer" It is necessary to edit this change in every tokenizer_config.json that you had for LLaMA so far. 2023-03-16 10:16:17 -04:00			`git+https://github.com/huggingface/transformers`