Update README.md

Add function calling configuration

README.md

@@ -38,7 +38,7 @@ license: apache-2.0
 # OpenVINO IR model with int8 quantization of Hermes-2-Theta-Llama-3-8B
 
 Model definition for LocalAI:
-```
+```yaml
 name: hermes-2-Theta-llama3
 backend: transformers
 parameters:
@@ -49,6 +49,74 @@ template:
   use_tokenizer_template: true
 ```
 
+LocalAI configuration for function calling:
+```yaml
+name: hermes-2-Theta-llama3
+backend: transformers
+parameters:
+  model: fakezeta/Hermes-2-Theta-Llama-3-8B-ov-int8
+context_size: 8192
+type: OVModelForCausalLM
+function:
+  # disable injecting the "answer" tool
+  disable_no_action: true
+  # This allows the grammar to also return messages
+  grammar_message: true
+  # Suffix to add to the grammar
+  grammar_prefix: '<tool_call>\n'
+  return_name_in_function_response: true
+  # Without grammar uncomment the lines below
+  # Warning: this is relying only on the capability of the
+  # LLM model to generate the correct function call.
+  # no_grammar: true
+  # json_regex_match: "(?s)<tool_call>(.*?)</tool_call>"
+  replace_results: 
+    "<tool_call>": ""
+    "\'": "\""
+
+template:
+    chat_message: |
+      <|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>
+      {{- else if eq .RoleName "tool" }}
+      <tool_response>
+      {{- end }}
+      {{- if .Content}}
+      {{.Content }}
+      {{- end }}
+      {{- if .FunctionCall}}
+      {{toJson .FunctionCall}}
+      {{- end }}
+      {{- if .FunctionCall }}
+      </tool_call>
+      {{- else if eq .RoleName "tool" }}
+      </tool_response>
+      {{- end }}<|im_end|>
+    # https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF#prompt-format-for-function-calling
+    function: |
+      <|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>
+    chat: |
+      {{.Input -}}
+      <|im_start|>assistant
+    completion: |
+      {{.Input}}
+```
 
 To run the model directly with LocalAI:
 ```