Model Goal request.
Hello, I've been enjoying your previous 2 24b models, Trifecta-Max and Dark-Triad, and I plan on giving this a spin too once a q8 gguf is available (I've put in a request to mradermacher.)
I was wandering, would it be possible to get a bit of insight into your idea behind each model? Just a line or two about the intent, to be included in the model card? It's just, without downloading and using these models for an extended time, there's no real way to see what the intended difference is between say, Dark-Triad and this model?
No worries if you're not interested, I just figured it couldn't hurt to ask.
Hello, really appreciate the kind words and glad you've been enjoying the previous models! To be honest, right now I’m mostly experimenting, trying out different merging techniques and parameter setups using the models that are already pretty good. Models like Trifecta-Max, Dark-Triad, and now Pinecone-Sage are quite close in general use, and the differences can be subtle. That said, I’m planning to move into more advanced stuff like SFT, DPO, and QLoRA soon, and as that happens, the intent behind each model will get clearer. For now, it’s a bit of creative exploration and learning through iteration.