Spiking brain 7 b
Create a fine tuning of spiking brain 7 n
Create a fine tuning of spiking brain 7 n
Create what finetune of what? I can't even find a model named "spiking brain 7 n" so please provide a link. Team mradermacher provides GGUF quants and doesn't do finetunes. I might personally make one if I like your idea but for now, I don't even know what you want.
Quantized model of this https://github.com/BICLab/SpikingBrain-7B and also request for fine-tuning this to a coding model
The linked GitHub repository does unfortunately not contain any model despite the author claiming it to do so. I downloaded it and it is only 6.87 MB when ZIP compressed which is obviously way too small for it to contain any model.
The model is of architecture GLAswaForCausalLM which is not currently by llama.cpp. Some developer would need to follow https://github.com/ggml-org/llama.cpp/blob/master/docs/development/HOWTO-add-model.md and implementing GLAswaForCausalLM support inside llama.cpp before we can quantize. Kind of a shame as I'm starting to like the model and with not even vLLM supporting GLAswaForCausalLM I'm having a hard time even trying it.