mirror of
https://github.com/mudler/LocalAI.git
synced 2024-06-07 19:40:48 +00:00
e533dcf506
* feat(startup): allow to specify models from local files * feat(aio): add Dockerfile, make targets, aio profiles * feat(template): add Function and LastMessage * add hermes2-pro-mistral * update hermes2 definition * feat(template): add sprig * feat(template): expose FunctionCall * feat(aio): switch llm for text
41 lines
1.2 KiB
YAML
41 lines
1.2 KiB
YAML
backend: llama-cpp
|
|
context_size: 4096
|
|
f16: true
|
|
|
|
gpu_layers: 90
|
|
mmap: true
|
|
name: llava
|
|
|
|
roles:
|
|
user: "USER:"
|
|
assistant: "ASSISTANT:"
|
|
system: "SYSTEM:"
|
|
|
|
mmproj: bakllava-mmproj.gguf
|
|
parameters:
|
|
model: bakllava.gguf
|
|
temperature: 0.2
|
|
top_k: 40
|
|
top_p: 0.95
|
|
seed: -1
|
|
mirostat: 2
|
|
mirostat_eta: 1.0
|
|
mirostat_tau: 1.0
|
|
|
|
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:
|
|
|
|
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": "llava",
|
|
"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}]}'
|