ranking
when you think you open a ranking for your models ?
@kalle07 I am running some llm eval harness, it's just taking so long! I was thinking to just submit the none-quantized to HF leaderboard, but even there it takes forever. I think I would go with a manually selected ones specially if they are downloaded the most just to have more info on the model card.
seem you over read that ?!??
"
Of course!
I don't believe anyone merged quantized models and got anything interesting. It's always better to work with 16/32 bit, and then quantize the result. So I go with the default that loads the models in 16bit
Marcoroni, Hermes, Redmond-Puffin, OpenHermes, SlimOrca, Orca, supermario I actually really like some of these! So I will attack the original models first, merge them with different fine-tuned models from the same architecture.
I am going to find out if we have models based on let's say Hermes that are purely chat(human) and purely instruct(knowlidge) and merge them with different techniques, evaluate, and see the results. Different languages, different fine-tune techniques are interesting for merges
I have done fine-tuning, but it was mostly prompt-based via instructions. To learn from a plain text, usually RAG would be a better option to pair some chunks with prompt/instructions to mimic the tone/style of writing, etc.
"
hey... omg i could not write 4 days because there was a fault(in hugginface) with newcommers . . .
okay that looks like you have a plan ;)
what RAG software you use ?
all i tryed is GPT4all and privateGPT, the superbooga extention in obadooga dont work.
you have any suggestion, but i dont want use any accesses or keys and it would be nice if it had a small GUI.
btw all these based models have the knowledge of at least "wiki", so why is it so complicate to add some PDF books to any model, give it a simple way ?
another question, you have any idea what embedings models for RAG are and how the pytorch model is quantized to gguf ?
THX
Oh that! Of course! I am planning to start manually merging some of these with more targeted script and share them
what RAG software you use ?
all i tryed is GPT4all and privateGPT, the superbooga extention in obadooga dont work.
you have any suggestion, but i dont want use any accesses or keys and it would be nice if it had a small GUI.
btw all these based models have the knowledge of at least "wiki", so why is it so complicate to add some PDF books to any model, give it a simple way ?
another question, you have any idea what embedings models for RAG are and how the pytorch model is quantized to gguf ?