Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[D] Best method to retrain or augment llm on proprietary or specialized material? (alien.top)

submitted 1 year ago by spacedragon13@alien.top to c/machinelearning@academy.garden

1 comments fedilink hide all child comments

My boss is a semi famous author in a niche academic field. I have thousands of pages of text coming from books, transcripts, and more.

Is there a straightforward path to creating a corpus to augment Bert or Llama or another llm? End goal being able to chat with this ai that is now trained on his life's work.

Is there anything specific to understand in terms of preparing the corpus? Do I need key value pairs where I write a ton of examples questions and responses?

you are viewing a single comment's thread
view the rest of the comments

[–] Mammoth-Doughnut-160@alien.top 1 points 1 year ago

Agree that you should look at RAG. LLMs are not search engines so you need to connect the knowledge corpus to LLMs.

Try LLMWare's RAG implementation - it is easy to use, straightforward, and automates Mongo and Milvus set up so great for what you are trying to achieve. LLMWare also has free models in Hugging Face you can start to experiment with for experimenting for your use case.

https://github.com/llmware-ai/llmware

https://huggingface.co/llmware