Open Llama 7B 1T is released

#2
by ReadySetFly - opened

Hello @vihangd , would you kindly consider quantizing the full release model? Also there are some new quantized methods such as q4_K_M and others, would you kindly consider those additional methods if you do the former?

ReadySetFly changed discussion status to closed

@ReadySetFly I didn't upload the latest one since other folks have already uploaded it this since this the final version. I would recommend SlyEcho/open_llama_7b_ggml repo. I think this has all the quantizations if not please let me know and I will upload the same if required..

Sign up or log in to comment