Darren Oberst

@thinkmn - we have merged a proposed fix into the main branch - could you check it out and confirm if this will meet your needs in terms of configuration...

@Clima2024 - happy to help with this - and sorry that you have run into an issue ... without sharing any confidential information, could you share the key 2-3 line...

@sayansinha2019 - thanks for sharing this case. There may not be a perfect solution - likely will require a little bit of experimentation and trial and error.... We will note...

@Arwin567 - thanks for sharing this and sorry that you ran into an issue. I suspect the problem is that "industry-bert-contracts" is an embedding model, not a generative model. So,...

@Arwin567 - yes, definitely, the industry-bert-contracts model is great for building semantic embeddings on contracts and other legal documents. Hope it is progressing well! Will close this thread.

@williamsokol - thanks for sharing this and sorry that you ran into an issue with this example. If no database is specified, then by default, LLMWare will look for Mongo....

The example has been updated too to explicitly show setting the LLMWareConfig().set_active_db parameter. Marking the issue as closed.

@HaozhiTan - thanks for raising - we will look into it ....

@HaozhiTan - quick update - we ran several tests with 'bartowski/Meta-Llama-3-8B-Instruct-GGUF' on several different platforms (Mac M1, Windows with CUDA, Linux with CUDA) and did not experience any issues -...

Closing the issue due to inactivity - and that model is working in our testing. @HaozhiTan - if you continue to have any issues with Llama-3 GGUF model, could you...