chore(model gallery): add nousresearch_deephermes-3-llama-3-8b-preview (#4828)

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

gallery/deephermes.yaml

@@ -0,0 +1,59 @@
+---
+name: "deephermes"
+
+config_file: |
+  mmap: true
+  context_size: 8192
+  stopwords:
+  - "<|im_end|>"
+  - "<dummy32000>"
+  - "<|eot_id|>"
+  - "<|end_of_text|>"
+  function:
+    disable_no_action: true
+    grammar:
+      triggers:
+        word: "<tool_call>"
+        at_start: false
+  template:
+    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 -}}
+      <tool_call>
+      {{ else if eq .RoleName "tool" -}}
+      <tool_response>
+      {{ end -}}
+      {{ if .Content -}}
+      {{.Content -}}
+      </tool_response>
+      {{ else if .FunctionCall -}}
+      {{ toJson .FunctionCall -}}
+      </tool_call>
+      {{ end -}}
+      <|eot_id|>
+    function: |
+      <|start_header_id|>system<|end_header_id|>
+
+      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}}
+      {{toJson .}}
+      {{end}}
+      </tools>
+
+      Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"}
+
+      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><|eot_id|>{{.Input }}
+      <|start_header_id|>assistant<|end_header_id|>
+    chat: |
+      {{.Input }}
+      <|start_header_id|>assistant<|end_header_id|>
+    completion: |
+      {{.Input}}

gallery/index.yaml

@@ -5744,6 +5744,30 @@
     - filename: ilsp_Llama-Krikri-8B-Instruct-Q4_K_M.gguf
       sha256: 0ae3a259f03ed79ba634a99ee3bfc672d785b5594b2f71053ed8cb760098abb6
       uri: huggingface://bartowski/ilsp_Llama-Krikri-8B-Instruct-GGUF/ilsp_Llama-Krikri-8B-Instruct-Q4_K_M.gguf
+- !!merge <<: *llama31
+  name: "nousresearch_deephermes-3-llama-3-8b-preview"
+  url: "github:mudler/LocalAI/gallery/deephermes.yaml@master"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/9fxlaDxteqe3SasZ7_06_.jpeg
+  urls:
+    - https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview
+    - https://huggingface.co/bartowski/NousResearch_DeepHermes-3-Llama-3-8B-Preview-GGUF
+  description: |
+    DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model. We have also improved LLM annotation, judgement, and function calling.
+
+    DeepHermes 3 Preview is one of the first LLM models to unify both "intuitive", traditional mode responses and long chain of thought reasoning responses into a single model, toggled by a system prompt.
+
+    Hermes 3, the predecessor of DeepHermes 3, is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.
+
+    The ethos of the Hermes series of models is focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.
+
+    This is a preview Hermes with early reasoning capabilities, distilled from R1 across a variety of tasks that benefit from reasoning and objectivity. Some quirks may be discovered! Please let us know any interesting findings or issues you discover!
+  overrides:
+    parameters:
+      model: NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
+  files:
+    - filename: NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
+      sha256: de36671bcfc78636dc3c1be4b702198c9d9e0b8abe22dc644e4da332b31b325f
+      uri: huggingface://bartowski/NousResearch_DeepHermes-3-Llama-3-8B-Preview-GGUF/NousResearch_DeepHermes-3-Llama-3-8B-Preview-Q4_K_M.gguf
 - &deepseek
   url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" ## Deepseek
   name: "deepseek-coder-v2-lite-instruct"