David
David
### Describe the bug Clean install following the instructions from the tutorial. I can run 7B and 13b Int4 weight nicely, but from the same torrent the 30B and 65B...
When I try and use the model, I see errors on very layer in the model: ``` size mismatch for model.layers.77.mlp.down_proj.scales: copying a param with shape torch.Size([8192, 1]) from checkpoint,...
Trying to install this on a Jetson Orin NX 16Gb. I get the following error: ``` $ conda install -c mlc-ai -c conda-forge mlc-chat-nightly Collecting package metadata (current_repodata.json): done Solving...
Adds access to the environment variable "OPENAI_API_ENGINE", which is needed for the Azure API. The Azure API requires the use of the 'engine' parameter in the ChatCompletion and not the...
Can the adapter be retrained to work with Llama-3-8B, which should perform much better than Vincuna-13B?
Generally, for a given system (mostly based around GPU or system architecture and RAM), there will be an optimal LLM size.and context. We should probably have settings for Mac's based...
As we seems to have a community around this project, I think we need a logo! Please post your ideas (they of course are allowed to be AI Generated 👍)...
I found this site on Github, but when I go to the link, I see it is listed at https://gethugothemes.com/ for $79 I am unsure if that link is for...
I would like to build a chatbot with a long context. However, if the context gets too long, to prevent going over the model's context limits, I want to be...
Just a few things to explore: - use a better version of Whisper, maybe WhisperX? (there's a [good blog post here](https://amgadhasan.substack.com/p/sota-asr-tooling-long-form-transcription)) - Find a smaller voice generation model (smaller VITS...