# Sample YAML file for configuration.
# Comment out values as needed. Every value has a default within the application.

# Unless specified in the comments, DO NOT put these options in quotes!
# You can use https://www.yamllint.com/ if you want to check your YAML formatting.

# Options for networking
network:
  # The IP to host on (default: 127.0.0.1).
  # Use 0.0.0.0 to expose on all network adapters
  host: 127.0.0.1

  # The port to host on (default: 5000)
  port: 5000

  # Disable HTTP token authenticaion with requests
  # WARNING: This will make your instance vulnerable!
  # Turn on this option if you are ONLY connecting from localhost
  disable_auth: False

# Options for logging
logging:
  # Enable prompt logging (default: False)
  prompt: False

  # Enable generation parameter logging (default: False)
  generation_params: False

# Options for model overrides and loading
model:
  # Overrides the directory to look for models (default: models)
  # Windows users, DO NOT put this path in quotes! This directory will be invalid otherwise.
  model_dir: models

  # An initial model to load. Make sure the model is located in the model directory!
  # A model can be loaded later via the API.
  model_name: A model name

  # Sends dummy model names when the models endpoint is queried
  # Enable this if the program is looking for a specific OAI model
  use_dummy_models: False

  # The below parameters apply only if model_name is set

  # Max sequence length (default: None)
  # Fetched from the model's base sequence length in config.json by default
  max_seq_len:

  # Overrides base model context length (default: None)
  # WARNING: Don't set this unless you know what you're doing!
  # Only use this if the model's base sequence length in config.json is incorrect (ex. Mistral/Mixtral models)
  override_base_seq_len:

  # Automatically allocate resources to GPUs (default: True)
  gpu_split_auto: True

  # An integer array of GBs of vram to split between GPUs (default: [])
  gpu_split: [20.6, 24]

  # Rope scale (default: 1.0)
  # Same thing as compress_pos_emb
  # Only use if your model was trained on long context with rope (check config.json)
  rope_scale: 1.0

  # Rope alpha (default: 1.0)
  # Same thing as alpha_value
  # Leave blank to automatically calculate alpha
  rope_alpha: 1.0

  # Disable Flash-attention 2. Set to True for GPUs lower than Nvidia's 3000 series. (default: False)
  no_flash_attention: False

  # Enable 8 bit cache mode for VRAM savings (slight performance hit). Possible values FP16, FP8. (default: FP16)
  cache_mode: FP16

  # Set the prompt template for this model. If empty, chat completions will be disabled. (default: None)
  # NOTE: Only works with chat completion message lists!
  prompt_template:

  # Number of experts to use per token. Loads from the model's config.json if not specified (default: None)
  # WARNING: Don't set this unless you know what you're doing!
  # NOTE: For MoE models (ex. Mixtral) only!
  num_experts_per_token:

  # Options for draft models (speculative decoding). This will use more VRAM!
  draft:
    # Overrides the directory to look for draft (default: models)
    draft_model_dir: models

    # An initial draft model to load. Make sure this model is located in the model directory!
    # A draft model can be loaded later via the API.
    draft_model_name: A model name
  
    # Rope scale for draft models (default: 1.0)
    # Same thing as compress_pos_emb
    # Only use if your draft model was trained on long context with rope (check config.json)
    draft_rope_scale: 1.0

    # Rope alpha for draft model (default: 1.0)
    # Same thing as alpha_value
    # Leave blank to automatically calculate alpha value
    draft_rope_alpha: 1.0
  
  # Options for loras
  lora:
    # Overrides the directory to look for loras (default: loras)
    lora_dir: loras
    
    # List of loras to load and associated scaling factors (default: 1.0). Comment out unused entries or add more rows as needed.
    loras:
    - name: lora1
      scaling: 1.0
    - name: lora2
      scaling: 0.9
    - name: lora3
      scaling: 0.5