models(gallery): add llama3-32k

Signed-off-by: Ettore Di Giacinto <[email protected]>

Author: mudler

gallery/chatml.yaml

@@ -0,0 +1,41 @@
+---
+name: "chatml"
+
+config_file: |
+  mmap: true
+  template:
+    chat_message: |
+      <|im_start|>{{ .RoleName }}
+      {{- if .FunctionCall }}
+      Function call:
+      {{- else if eq .RoleName "tool" }}
+      Function response:
+      {{- end }}
+      {{- if .Content}}
+      {{.Content }}
+      {{- end }}
+      {{- if .FunctionCall}}
+      {{toJson .FunctionCall}}
+      {{- end }}
+      <|im_end|>
+    function: |
+      <|im_start|>system
+      You are a function calling AI model. You are provided with functions to execute. 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:
+      {{range .Functions}}
+      {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+      {{end}}
+      For each function call return a json object with function name and arguments
+      <|im_end|>
+      {{.Input -}}
+      <|im_start|>assistant
+      <tool_call>
+    chat: |
+      {{.Input -}}
+      <|im_start|>assistant
+    completion: |
+      {{.Input}}
+  context_size: 4096
+  f16: true
+  stopwords:
+  - <|im_end|>
+  - <dummy32000>

gallery/index.yaml

@@ -412,6 +412,25 @@
     - filename: dolphin-2.9-llama3-8b-q6_K.gguf
       sha256: 8aac72a0bd72c075ba7be1aa29945e47b07d39cd16be9a80933935f51b57fb32
       uri: huggingface://cognitivecomputations/dolphin-2.9-llama3-8b-gguf/dolphin-2.9-llama3-8b-q6_K.gguf
+- url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
+  name: "llama-3-8b-instruct-dpo-v0.3-32k"
+  license: llama3
+  urls:
+    - https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+    - llama3
+  overrides:
+    context_size: 32768
+    parameters:
+      model: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
+  files:
+    - filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
+      sha256: 694c55b5215d03e59626cd4292076eaf31610ef27ba04737166766baa75d889f
+      uri: huggingface://MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF/Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
 ## LLama2 and derivatives
 ### Start Fimbulvetr
 - &vicuna-chat