James Coleman

You need to select a sampler in the advanced options above the dream button.

So, as I understand it: 1. Get fail2ban to parse IPv6 addresses from logs. I don't think they are logged differently from IPv4. 2. At first, have it detect only...

To add caching: ```nginx proxy_cache_path /assets/cache keys_zone=fallback_cache:30720m levels=1:2 max_size=30720m inactive=30d; proxy_buffer_size 128k; proxy_buffers 4 256k; proxy_busy_buffers_size 256k; server { listen 80; resolver 8.8.8.8; location / { root /assets; autoindex on;...

I'm assuming they do not have an IPv6 Address yet which is weird as even my server has one. When IPv6 is available, can you do the following with it:...

@HarriL I do not see how ipify can be compromised if it is just a proxy to golang... @JJC1138 My reason for having IPv6 support in ipify is so that...

``` pip3 uninstall transformers pip3 install transformers==4.26.1 ```

One thing you could possibly do to support multiple LLM models, utilize an existing LLM webui and their API. The one I'm familiar with is https://github.com/oobabooga/text-generation-webui/blob/main/api-examples/api-example-chat.py which has an fairly...

Sounds like you have a plan together that is well thought out. I am thankful that you decided to make this project open source, will be happy to help if...

Giving it a try on my P41, I ran across a bug which is fixed upstream but not yet in a release: ``` willow-inference-server-wis-1 | [2023-06-21 17:20:39 +0000] [89] [INFO]...

Wow, you're right... Running the text-generation-webui on the P41 is slow. Was hoping to save a buck by getting it. ``` Output generated in 47.55 seconds (0.61 tokens/s, 29 tokens,...