dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-03 09:24:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 24

feat(aio): update AIO image defaults (#5002)

Browse source 
* feat(aio): update AIO image defaults

cpu:
 - text-to-text: llama3.1
 - embeddings: granite-embeddings
 - vision: moonream2

gpu/intel:
 - text-to-text: localai-functioncall-qwen2.5-7b-v0.5
 - embeddings: granite-embeddings
 - vision: minicpm

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

* feat(aio): use minicpm as moondream2 stopped working

https://github.com/ggml-org/llama.cpp/pull/12322#issuecomment-2717483759

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-12 12:55:06 +01:00 • committed by GitHub
parent e878556e98
commit 9f5dcf2d1e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 244 additions and 339 deletions
Download patch file Download diff file Expand all files Collapse all files

69
aio/intel/vision.yaml
View file

@ -1,35 +1,50 @@
backend: llama-cpp
context_size: 4096
mmap: false
f16: false
f16: true
mmap: true
mmproj: minicpm-v-2_6-mmproj-f16.gguf
name: gpt-4o
roles:
user: "USER:"
assistant: "ASSISTANT:"
system: "SYSTEM:"
mmproj: llava-v1.6-7b-mmproj-f16.gguf
parameters:
model: llava-v1.6-mistral-7b.Q5_K_M.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
seed: -1
model: minicpm-v-2_6-Q4_K_M.gguf
stopwords:
- <|im_end|>
- <dummy32000>
- </s>
- <|endoftext|>
template:
chat: |
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
{{.Input -}}
<|im_start|>assistant
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|>
completion: |
{{.Input}}
ASSISTANT:
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
download_files:
- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.gguf
- filename: llava-v1.6-7b-mmproj-f16.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf
usage: |
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "gpt-4-vision-preview",
"messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'
- filename: minicpm-v-2_6-Q4_K_M.gguf
sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
- filename: minicpm-v-2_6-mmproj-f16.gguf
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd