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>
This commit is contained in:
Ettore Di Giacinto 2025-03-12 11:48:10 +01:00
parent e878556e98
commit a0faf87ec2
9 changed files with 224 additions and 341 deletions

View file

@ -1,31 +1,27 @@
backend: llama-cpp
context_size: 4096
context_size: 2046
f16: true
mmap: true
mmproj: moondream2-mmproj-f16.gguf
name: gpt-4o
roles:
user: "USER:"
assistant: "ASSISTANT:"
system: "SYSTEM:"
mmproj: bakllava-mmproj.gguf
parameters:
model: bakllava.gguf
model: moondream2-text-model-f16.gguf
roles:
assistant: "\nAnswer: "
system: "\nSystem: "
user: "\nQuestion: "
stopwords:
- 'Question:'
- <|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}}
ASSISTANT:
Answer:
completion: |
Complete the following sentence: {{.Input}}
download_files:
- filename: bakllava.gguf
uri: huggingface://mys/ggml_bakllava-1/ggml-model-q4_k.gguf
- filename: bakllava-mmproj.gguf
uri: huggingface://mys/ggml_bakllava-1/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: moondream2-text-model-f16.gguf
sha256: 4e17e9107fb8781629b3c8ce177de57ffeae90fe14adcf7b99f0eef025889696
uri: huggingface://moondream/moondream2-gguf/moondream2-text-model-f16.gguf
- filename: moondream2-mmproj-f16.gguf
sha256: 4cc1cb3660d87ff56432ebeb7884ad35d67c48c7b9f6b2856f305e39c38eed8f
uri: huggingface://moondream/moondream2-gguf/moondream2-mmproj-f16.gguf