diff --git a/embedded/models/phi-2-orange.yaml b/embedded/models/phi-2-orange.yaml new file mode 100644 index 00000000000..9207d2832c5 --- /dev/null +++ b/embedded/models/phi-2-orange.yaml @@ -0,0 +1,30 @@ +name: phi-2-chat +mmap: true +parameters: + model: huggingface://l3utterfly/phi-2-orange-GGUF/phi-2-orange.Q6_K.gguf + +template: + chat_message: | + <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}} + {{if .Content}}{{.Content}}{{end}} + <|im_end|> + chat: | + {{.Input}} + <|im_start|>assistant + completion: | + {{.Input}} +context_size: 4096 +f16: true +stopwords: +- <|im_end|> +- + +description: | + This model is a chatbot that can be used for general conversation. + [Model card](https://huggingface.co/TheBloke/phi-2-orange-GGUF) + +usage: | + curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ + "model": "phi-2-chat", + "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}] + }'