name: codellama-7b-gguf
backend: transformers
parameters:
  model: huggingface://TheBloke/CodeLlama-7B-GGUF/codellama-7b.Q4_K_M.gguf
  temperature: 0.5
  top_k: 40
  seed: -1
  top_p: 0.95
mirostat: 2
mirostat_eta: 1.0
mirostat_tau: 1.0

context_size: 4096
f16: true
gpu_layers: 90
usage: |
      curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
          "model": "codellama-7b-gguf",
          "prompt": "import socket\n\ndef ping_exponential_backoff(host: str):"
      }'