Adding modelsConfigs to be able to configure models with helm.
Why:
for file in /models-configs/*; do
filename=$(basename "$file")
if [[ $filename != *.yaml ]]; then
cp -fL "$file" "/models/$filename.yaml"
else
cp -fL "$file" "/models/$filename"
fi
done
Because I would like to make it usable with questions.yaml (used by Rancher and Taikun for example).
Example:
modelsConfigs:
phi-2: |
name: phi-2
context_size: 2048
f16: true
#gpu_layers: 90
mmap: true
trimsuffix:
- "\n"
parameters:
model: huggingface://TheBloke/phi-2-GGUF/phi-2.Q8_0.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
seed: -1
template:
chat: &template |-
Instruct: {{.Input}}
Output:
completion: *template
usage: |
To use this model, interact with the API (in another terminal) with curl for instance:
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "phi-2",
"messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
}'
Adding modelsConfigs to be able to configure models with helm.
Why:
Because I would like to make it usable with questions.yaml (used by Rancher and Taikun for example).
Example: