GGUF
llama-cpp
Inference Endpoints
imatrix
conversational

How use

#1
by maixrock - opened

I am a beginner, and I am interested in exploring this model file. How can I use it in LM Studio or apply this model to other tasks? Unfortunately, I couldn’t figure it out from the description. When I try to load it into LM Studio as usual, I get an error:

Error rendering prompt with jinja template: SyntaxError: Unknown statement type: Identifier

Intelligent Estate org
edited 3 days ago

These models are built for local use. here is a good article on model use in LMstudio, I simply download the file and place it in my local GGUF models repo or specified folder on my machine. if you are using it with RAG try to distribute your chat Rag and GGUF file in seperate locations if possible and it can speed things up for you. If you are using it on an Orange Pi zero2w make sure to use a small M.2. drive.

GPT4ALL is a good place to start if you are beginning.

https://huggingface.co/blog/yagilb/lms-hf

Cant download. Gives a 403 :(

Intelligent Estate org

I mean directly from the files and settings tab. there should be an arrow next to the file size. the model is now gated as it's a possible level 2 threat but it should be available to users on huggingface

Yep clicking that arrow gives the 403

Intelligent Estate org

Ok that's a browser issue, try using a different browser to download, or check your browser settings.

Intelligent Estate org

Good Luck. Leave some feedback, it should be functional on older systems and edge devices

Sign up or log in to comment