taozhiyuai

works on safari.thx

my model file works fine. # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM llama3:8b-instruct-fp16 FROM...

> create from gguf 7b q4, it's the same problem while `ollama run` > > ```shell > $ ollama -v > ollama version is 0.1.32 > > $ ollama show...

I import gguf from https://hf-mirror.com/second-state/Octopus-v2-GGUF

I think It take too long time to generate tokens.

14B generates only 2 actions. so I think 7B is the best model size on my laptop.

> You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > Or use a base model, then create a new model...

> > > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > > Or use a base model, then create...

> > > You can change template, system and params in Modelfile, then recreate model and repush model to ollama. > > > Or use a base model, then create...

q6k is weird. works fine for q4 or q5. same model file. so strange