solitude-alive

How to fine-tune Gemma with pytorch? There seems to be fine-tuning code on Huggingface, but it cannot be used directly. Thanks

Gemma lora

2

#### Context - Create lora fine-tune for Gemma model. #### Changelog - ... #### Test plan - .... It can work with `apply_lora_to_mlp = True, apply_lora_to_output = False`, but not...

Will it support RAG?

2

Do you have plans to support Retrieval-Augmented-Generation (RAG), constructing a vector database based on personal data and then performing the corresponding retrieval and generation processes?

Support for Custom base_url to Use Locally Deployed LLMs

8

Hello, First of all, thank you for this amazing project. I find it extremely useful, and I appreciate all the effort that's gone into it. I have a feature request...