Hey everyone, happy to say I’m officially announcing Obsidian V0.5 as part of my work at Nous Research and building upon my work creating the Capybara V1.9 dataset.
This model is blazing fast and is likely the first Multi-modal model that is efficient enough to fit within the ram constraints of even a non-pro iphone! at practical speeds as well!
This model in its current state is largely a multi-modal version of Nous-Capybara-3B which I also only recently released, I’ve designed the dataset with novel synthesis methods (Paper currently being done) it’s made to be robust with conversational abilities and even includes multi-turn data that has been synthesized as a continuation of single turn data examples contained within datasets like Airoboros, Know_logic, EverythingLM and more.
It’s built using Llava 1.5 techniques but instead of a 7B llama as a base, we choose to use the new StableLM 3B model trained for 4 trillion tokens. (We plan to train upon Mistral likely as well)
Any questions or feedback are much appreciated!
Download here: https://huggingface.co/NousResearch/Obsidian-3B-V0.5
Or download quantized version here, Courtesy of Nisten: https://huggingface.co/nisten/obsidian-3b-multimodal-q6-gguf
Even the quantised version seems to be working pretty well with the
stablelm-supportbranch, but either the template or model is missing the end token or the LlamaCPP branch isn’t quite ready as the output just keeps going…Does anyone else have the same problem and know what to do?
This is how I interpreted the template from the model card:
https://preview.redd.it/eqxvq2lefjxb1.png?width=1240&format=png&auto=webp&s=b5c1f1550b50fcf16ab1177894b890b852cf65a9