A Gradio web UI for Large Language Models with support for multiple inference backends. - oobabooga/text-generation-webui
https://colab.research.google.com/github/oobabooga/text-generation-webui/blob/main/Colab-TextGen-GPU.ipynb Acknowledgment In August 2023, Andreessen Horowitz (a16z) provided a generous grant to encourage and support my independent work on this project. I am extremely grateful for their trust and...
三、Colab在线跑 pyg-13b-GPTQ-4bit-128g https://colab.research.google.com/github/camenduru/text-generation-webui-colab/blob/main/pyg-13b-GPTQ-4bit-128g.ipynb vicuna-13B-1.1-GPTQ-4bit-128g https://colab.research.google.com/github/camenduru/text-generation-webui-colab/blob/main/vicuna-13...
This is useful for running the web UI on Google Colab or similar. --auto-launch Open the web UI in the default browser upon launch. --gradio-auth-path GRADIO_AUTH_PATH Set the gradio authentication file path. The file should contain one or more user:password pairs in this format: "u1...
Im using Oobabooga on colab and I've noticed that the AI is more restricted and not giving uncensored answers like before. I tried changing the model, but it still avoids NSFW topics. How can I make it uncensored like before?
Describe the bug After updating to the commit, exllamav2 can no longer run inference on Nvidia GPUs that are older than Ampere (anything under consumer RTX 3xxx or the equivalent Axxx GPU). This is because flash-attn v2.0.0 and greater r...
Running into the same issue on Google Colab. API simply isn't exposed, neither from --api, or --public-api. I don't even get an error, though. Nvm, I'm incredibly dumb, completely forgot that my custom notebook has a model selector, only one of the models has the --api paramete...
Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly Cancel Create saved search Sign in Sign up Reseting focus {{ message }} oobabooga / text-generation-webui Public Notifications You must be signed in to change notification settings Fork 5....
Activate text streaming: When unchecked, the full response is outputted at once, without streaming the words one at a time. I recommend unchecking this parameter on high latency networks like running the webui on Google Colab or using--share. ...
Describe the bug When using the google colab for XTTS_v2 that is linked in the official tutorial it throws an error in the second step: ImportError: tokenizers>=0.19,<0.20 is required for a normal functioning of this module, but found to...