models(gallery): add wizardlm2

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

Author: mudler

gallery/index.yaml

@@ -520,6 +520,33 @@
     - filename: Noromaid-13B-0.4-DPO.q4_k_m.gguf
       sha256: cb28e878d034fae3d0b43326c5fc1cfb4ab583b17c56e41d6ce023caec03c1c1
       uri: huggingface://NeverSleep/Noromaid-13B-0.4-DPO-GGUF/Noromaid-13B-0.4-DPO.q4_k_m.gguf
+### START Vicuna based
+- &wizardlm2
+  url: "github:mudler/LocalAI/gallery/wizardlm2.yaml@master"
+  name: "wizardlm2-7b"
+  description: |
+    We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent. New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.
+
+      WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works and consistently outperforms all the existing state-of-the-art opensource models.
+      WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
+      WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.
+  icon: https://github.com/nlpxucan/WizardLM/raw/main/imgs/WizardLM.png
+  license: apache-2.0
+  urls:
+    - https://huggingface.co/MaziyarPanahi/WizardLM-2-7B-GGUF
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+    - mistral
+  overrides:
+    parameters:
+      model: WizardLM-2-7B.Q4_K_M.gguf
+  files:
+    - filename: WizardLM-2-7B.Q4_K_M.gguf
+      sha256: 613212417701a26fd43f565c5c424a2284d65b1fddb872b53a99ef8add796f64
+      uri: huggingface://MaziyarPanahi/WizardLM-2-7B-GGUF/WizardLM-2-7B.Q4_K_M.gguf
 ### START LLaVa
 - &llava
   url: "github:mudler/LocalAI/gallery/llava.yaml@master"

gallery/wizardlm2.yaml

@@ -0,0 +1,15 @@
+---
+name: "wizardlm2"
+
+config_file: |
+  mmap: true
+  template:
+    chat_message: |-
+      {{if eq .RoleName "assistant"}}ASSISTANT: {{.Content}}</s>{{else if eq .RoleName "system"}}{{.Content}}{{else if eq .RoleName "user"}}USER: {{.Content}}{{end}}
+    chat: "{{.Input}}ASSISTANT: "
+    completion: |-
+      {{.Input}}
+  context_size: 32768
+  f16: true
+  stopwords:
+  - </s>