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

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

@@ -1551,7 +1551,7 @@
       sha256: edc50f6c243e6bd6912599661a15e030de03d2be53409663ac27d3ca48306ee4
       uri: huggingface://mudler/LocalAI-functioncall-llama3.2-3b-v0.5-Q4_K_M-GGUF/localai-functioncall-llama3.2-3b-v0.5-q4_k_m.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -3512,7 +3512,7 @@
       sha256: 0fec82625f74a9a340837de7af287b1d9042e5aeb70cda2621426db99958b0af
       uri: huggingface://bartowski/Chuluun-Qwen2.5-72B-v0.08-GGUF/Chuluun-Qwen2.5-72B-v0.08-Q4_K_M.gguf
 - &smollm
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## SmolLM
   name: "smollm-1.7b-instruct"
   icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
   tags:
@@ -3803,7 +3803,7 @@
       sha256: 6795de6e7025e4a77042232908fe7be304b6b6b465c5feb71ba6861f37038aaf
       uri: huggingface://bartowski/open-thoughts_OpenThinker-32B-GGUF/open-thoughts_OpenThinker-32B-Q4_K_M.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578
   name: "meta-llama-3.1-8b-instruct"
   license: llama3.1
@@ -5744,8 +5744,32 @@
     - 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"
   icon: "https://avatars.githubusercontent.com/u/148330874"
   license: deepseek
@@ -5810,7 +5834,7 @@
       sha256: a47782c55ef2b39b19644213720a599d9849511a73c9ebb0c1de749383c0a0f8
       uri: huggingface://RichardErkhov/ContextualAI_-_archangel_sft_pythia2-8b-gguf/archangel_sft_pythia2-8b.Q4_K_M.gguf
 - &deepseek-r1
   url: "github:mudler/LocalAI/gallery/deepseek-r1.yaml@master" ## Start DeepSeek-R1
   name: "deepseek-r1-distill-qwen-1.5b"
   icon: "https://avatars.githubusercontent.com/u/148330874"
   urls:
@@ -6038,7 +6062,7 @@
       sha256: bf51b412360a84792ae9145e2ca322379234c118dbff498ff08e589253b67ded
       uri: huggingface://bartowski/agentica-org_DeepScaleR-1.5B-Preview-GGUF/agentica-org_DeepScaleR-1.5B-Preview-Q4_K_M.gguf
 - &qwen2
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2
   name: "qwen2-7b-instruct"
   icon: https://avatars.githubusercontent.com/u/141221163
   license: apache-2.0
@@ -6439,7 +6463,7 @@
       sha256: dbffc989d12d42ef8e4a2994e102d7ec7a02c49ec08ea2e35426372ad07b4cd8
       uri: huggingface://bartowski/TAID-LLM-1.5B-GGUF/TAID-LLM-1.5B-Q4_K_M.gguf
 - &mistral03
   url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master" ## START Mistral
   name: "mistral-7b-instruct-v0.3"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/62dac1c7a8ead43d20e3e17a/wrLf5yaGC6ng4XME70w6Z.png
   license: apache-2.0
@@ -7157,7 +7181,7 @@
       sha256: 40025eb00d83c9e9393555962962a2dfc5251fe7bd70812835ff0bcc55ecc463
       uri: huggingface://bartowski/SicariusSicariiStuff_Redemption_Wind_24B-GGUF/SicariusSicariiStuff_Redemption_Wind_24B-Q4_K_M.gguf
 - &mudler
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models
   name: "LocalAI-llama3-8b-function-call-v0.2"
   icon: "https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/us5JKi9z046p8K-cn_M0w.webp"
   license: llama3
@@ -7202,7 +7226,7 @@
       sha256: 579cbb229f9c11d0330759ff4733102d2491615a4c61289e26c09d1b3a583fec
       uri: huggingface://mudler/Mirai-Nova-Llama3-LocalAI-8B-v0.1-GGUF/Mirai-Nova-Llama3-LocalAI-8B-v0.1-q4_k_m.bin
 - &parler-tts
   url: "github:mudler/LocalAI/gallery/parler-tts.yaml@master" ### START parler-tts
   name: parler-tts-mini-v0.1
   overrides:
     parameters:
@@ -7219,7 +7243,7 @@
     - text-to-speech
     - python
 - &rerankers
   url: "github:mudler/LocalAI/gallery/rerankers.yaml@master" ### START rerankers
   name: cross-encoder
   parameters:
     model: cross-encoder