More info about this model?
Is this just a gguf or has more finetuning been done, and if so on what?
Is this just a gguf or has more finetuning been done, and if so on what?
It's just GGUF with no finetuning done!
How was this GGUF created? I want to create a 128k context GGUF for non-instruct model.
How was this GGUF created? I want to create a 128k context GGUF for non-instruct model.
We utilized the YaRN methodology which has dynamic scaling
I am a machine learning newbie; I am more apt at writing apps that utilize LLMs. Currently, I am working on an Emacs package to use the non-instruct models for repo-level FIM code completion. For large repos where context length increases more than 32K, I don't have a GGUF to run using llama.cpp. I tried the instruct models, but they generate unreliable completions. I would really appreciate if you could upload large-context GGUFs for the non-instruct models, or point me in the direction so that I can create my own.