chore(model gallery): add LocalAI-functioncall-llama3.2-1b-v0.4 (#4740)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

gallery/index.yaml

@@ -853,7 +853,7 @@
       sha256: bac8e8c1d1d9d53cbdb148b8ff9ad378ddb392429207099e85b5aae3a43bff3d
       uri: huggingface://cstr/salamandra-7b-instruct-GGUF/salamandra-7b-instruct.Q4_K_M-f32.gguf
 - &llama32
-  url: "github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master" ## llama3.2
+  url: "github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master"
   icon: https://avatars.githubusercontent.com/u/153379578
   license: llama3.2
   description: |
@@ -1383,6 +1383,21 @@
     - filename: FineMath-Llama-3B-Q4_K_M.gguf
       sha256: 16c73b5cf2a417a7e1608bcc9469f1461fc3e759ce04a3a337f48df977dc158c
       uri: huggingface://bartowski/FineMath-Llama-3B-GGUF/FineMath-Llama-3B-Q4_K_M.gguf
+- !!merge <<: *llama32
+  name: "LocalAI-functioncall-llama3.2-1b-v0.4"
+  url: "github:mudler/LocalAI/gallery/llama3.2-fcall.yaml@master"
+  urls:
+    - https://huggingface.co/mudler/LocalAI-functioncall-llama3.2-1b-v0.4
+    - https://huggingface.co/mradermacher/LocalAI-functioncall-llama3.2-1b-v0.4-GGUF
+  description: |
+    A model tailored to be conversational and execute function calls with LocalAI. This model is based on llama 3.2 and has 1B parameter. Perfect for small devices.
+  overrides:
+    parameters:
+      model: LocalAI-functioncall-llama3.2-1b-v0.4.Q8_0.gguf
+  files:
+    - filename: LocalAI-functioncall-llama3.2-1b-v0.4.Q8_0.gguf
+      sha256: 547e57c2d3f17c632c9fd303afdb00446e7396df453aee62633b76976c407616
+      uri: huggingface://mradermacher/LocalAI-functioncall-llama3.2-1b-v0.4-GGUF/LocalAI-functioncall-llama3.2-1b-v0.4.Q8_0.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163

gallery/llama3.2-fcall.yaml

@@ -0,0 +1,48 @@
+---
+name: "llama3.2-fcall"
+
+config_file: |
+  mmap: true
+  function:
+    json_regex_match:
+    - "(?s)<Output>(.*?)</Output>"
+    capture_llm_results:
+      - (?s)<Thought>(.*?)</Thought>
+    replace_llm_results:
+      - key: (?s)<Thought>(.*?)</Thought>
+        value: ""
+    grammar:
+      properties_order: "name,arguments"
+  template:
+    chat: |
+      <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+      You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>
+      {{.Input }}
+      <|start_header_id|>assistant<|end_header_id|>
+    chat_message: |
+      <|start_header_id|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}<|end_header_id|>
+      {{ if .FunctionCall -}}
+      {{ else if eq .RoleName "tool" -}}
+      {{ end -}}
+      {{ if .Content -}}
+      {{.Content -}}
+      {{ else if .FunctionCall -}}
+      {{ toJson .FunctionCall -}}
+      {{ end -}}
+      <|eot_id|>
+    completion: |
+      {{.Input}}
+    function: |
+      <|start_header_id|>system<|end_header_id|>
+      You are an AI assistant that executes function calls, and these are the tools at your disposal:
+      {{range .Functions}}
+      {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+      {{end}}
+      <|eot_id|>{{.Input}}<|start_header_id|>assistant<|end_header_id|>
+  context_size: 8192
+  f16: true
+  stopwords:
+  - <|im_end|>
+  - <dummy32000>
+  - "<|eot_id|>"
+  - <|end_of_text|>