models/gpt-3.5-turbo.yaml

name: gpt-3.5-turbo
# Default model parameters
parameters:
  # Relative to the models path
  model: mistral-7b-instruct-v0.2.Q4_0.gguf
  # temperature
  temperature: 0.3
  # all the OpenAI request options here..

# Default context size
context_size: 512
threads: 10

# Enable prompt caching
prompt_cache_path: "alpaca-cache"
prompt_cache_all: true

# stopwords (if supported by the backend)
stopwords:
- "HUMAN:"
- "### Response:"
# define chat roles
roles:
  assistant: '### Response:'
  system: '### System Instruction:'
  user: '### Instruction:'
template:
  # template file ".tmpl" with the prompt template to use by default on the endpoint call. Note there is no extension in the files
  completion: completion
  chat: chat