taozhiyuai

# Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM llama3:70b-instruct-q8_0 FROM /Users/taozhiyu/Downloads/M-OLLAMA/Llama3.70B.Instruct.q8.0/Llama3.70B.Instruct.q8.0.gguf TEMPLATE """{{ if .System...

> Ollama模型的地址写这个： http://host.docker.internal:11434 这个管用

> There is a way to change characters, but it's not easy right now > > 1. You need to change the Diambra parameters here > > > 2. You...

> Instruct models just generate endless text? Is there a missing config file or something or are those models not actually "instruct"? same here. and not support chinese 

please update model information officially https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3

> @artem-zinnatullin and @vk2r can you re-pull the image you're using? I'm wondering if you pulled before we fixed the problem earlier today. on my Mac, it always speak English...

> @taozhiyuai I currently use Q6_K from https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF and this Modelfile: > > ``` > FROM ./Meta-Llama-3-8B-Instruct-Q6_K.gguf > TEMPLATE """{{ if .System }}system > > {{ .System }}{{ end }}user...

去llama factory问

eva-decord

xformers装不上