Added Hermes Pro 7B

examples/configurations/hermes-pro-7b/chat-message.tmpl

@@ -0,0 +1,10 @@
+<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
+{{- if .FunctionCall }}<tool_call>{{end}}
+{{- if eq .RoleName "tool" }}<tool_result>{{end }}
+{{- if .Content}}
+{{.Content}}
+{{- end }}
+{{- if .FunctionCall}}{{toJson .FunctionCall}}{{end }}
+{{- if .FunctionCall }}</tool_call>{{end }}
+{{- if eq .RoleName "tool" }}</tool_result>{{end }}
+<|im_end|>

examples/configurations/hermes-pro-7b/chat.tmpl

@@ -0,0 +1,2 @@
+{{.Input -}}
+<|im_start|>assistant\n

examples/configurations/hermes-pro-7b/completion.tmpl

@@ -0,0 +1 @@
+{{.Input}}

examples/configurations/hermes-pro-7b/function.tmpl

@@ -0,0 +1,17 @@
+<|im_start|>system
+You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+<tools>
+{{range .Functions}}
+{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+{{end}}
+</tools>
+Use the following pydantic model json schema for each tool call you will make:
+{'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']}
+For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+<tool_call>
+{'arguments': <args-dict>, 'name': <function-name>}
+</tool_call>
+<|im_end|>
+{{.Input -}}
+<|im_start|>assistant
+<tool_call>

examples/configurations/hermes-pro-7b/hermes-pro-7b.yaml

@@ -0,0 +1,29 @@
+backend: llama
+name: hermes-Pro-7b
+context_size: 512
+gpu_layers:  33
+f16: true
+mmap: false
+mmlock: false
+no_mulmatq: true
+low_vram: false
+threads: 11
+stopwords:
+- <|im_end|>
+- <|im_start|>
+- <dummy32000>
+- "\n</tool_call>"
+- "\n\n\n"
+parameters:
+  model: Hermes-2-Pro-Mistral-7B.Q6_K.gguf
+  temperature: 0.2
+  top_k: 40
+  top_p: 0.6
+  seed: -1
+feature_flags:
+  usage: false
+template:
+  chat_message: chat-message
+  function: function    
+  chat: chat
+  completion: completion