Config: Alter YAML generation script for formatting adherence

Properly add comments and newlines where they need to go.

Signed-off-by: kingbri <bdashore3@proton.me>

config_sample.yml

@@ -18,27 +18,27 @@ network:
   # Disable HTTP token authentication with requests.
   # WARNING: This will make your instance vulnerable!
   # Turn on this option if you are ONLY connecting from localhost.
-  disable_auth: False
+  disable_auth: false
 
   # Send tracebacks over the API (default: False).
   # NOTE: Only enable this for debug purposes.
-  send_tracebacks: False
+  send_tracebacks: false
 
   # Select API servers to enable (default: ["OAI"]).
   # Possible values: OAI, Kobold.
-  api_servers: ['OAI']
+  api_servers: ["OAI"]
 
 # Options for logging
 logging:
   # Enable prompt logging (default: False).
-  log_prompt: False
+  log_prompt: false
 
   # Enable generation parameter logging (default: False).
-  log_generation_params: False
+  log_generation_params: false
 
   # Enable request logging (default: False).
   # NOTE: Only use this for debugging!
-  log_requests: False
+  log_requests: false
 
 # Options for model overrides and loading
 # Please read the comments to understand how arguments are handled
@@ -49,16 +49,16 @@ model:
   model_dir: models
 
   # Allow direct loading of models from a completion or chat completion request (default: False).
-  inline_model_loading: False
+  inline_model_loading: false
 
   # Sends dummy model names when the models endpoint is queried.
   # Enable this if the client is looking for specific OAI models.
-  use_dummy_models: False
+  use_dummy_models: false
 
   # An initial model to load.
   # Make sure the model is located in the model directory!
   # REQUIRED: This must be filled out to load a model on startup.
-  model_name: 
+  model_name:
 
   # Names of args to use as a fallback for API load requests (default: []).
   # For example, if you always want cache_mode to be Q4 instead of on the inital model load, add "cache_mode" to this array.
@@ -67,21 +67,21 @@ model:
 
   # Max sequence length (default: Empty).
   # Fetched from the model's base sequence length in config.json by default.
-  max_seq_len: 
+  max_seq_len:
 
   # Overrides base model context length (default: Empty).
   # WARNING: Don't set this unless you know what you're doing!
   # Again, do NOT use this for configuring context length, use max_seq_len above ^
-  override_base_seq_len: 
+  override_base_seq_len:
 
   # Load model with tensor parallelism.
   # Falls back to autosplit if GPU split isn't provided.
   # This ignores the gpu_split_auto value.
-  tensor_parallel: False
+  tensor_parallel: false
 
   # Automatically allocate resources to GPUs (default: True).
   # Not parsed for single GPU users.
-  gpu_split_auto: True
+  gpu_split_auto: true
 
   # Reserve VRAM used for autosplit loading (default: 96 MB on GPU 0).
   # Represented as an array of MB per GPU.
@@ -108,7 +108,7 @@ model:
   # Size of the prompt cache to allocate (default: max_seq_len).
   # Must be a multiple of 256 and can't be less than max_seq_len.
   # For CFG, set this to 2 * max_seq_len.
-  cache_size: 
+  cache_size:
 
   # Chunk size for prompt ingestion (default: 2048).
   # A lower value reduces VRAM usage but decreases ingestion speed.
@@ -119,23 +119,23 @@ model:
   # Set the maximum number of prompts to process at one time (default: None/Automatic).
   # Automatically calculated if left blank.
   # NOTE: Only available for Nvidia ampere (30 series) and above GPUs.
-  max_batch_size: 
+  max_batch_size:
 
   # Set the prompt template for this model. (default: None)
   # If empty, attempts to look for the model's chat template.
   # If a model contains multiple templates in its tokenizer_config.json,
   # set prompt_template to the name of the template you want to use.
   # NOTE: Only works with chat completion message lists!
-  prompt_template: 
+  prompt_template:
 
   # Number of experts to use per token.
   # Fetched from the model's config.json if empty.
   # NOTE: For MoE models only.
   # WARNING: Don't set this unless you know what you're doing!
-  num_experts_per_token: 
+  num_experts_per_token:
 
   # Enables fasttensors to possibly increase model loading speeds (default: False).
-  fasttensors: False
+  fasttensors: false
 
 # Options for draft models (speculative decoding)
 # This will use more VRAM!
@@ -145,7 +145,7 @@ draft_model:
 
   # An initial draft model to load.
   # Ensure the model is in the model directory.
-  draft_model_name: 
+  draft_model_name:
 
   # Rope scale for draft models (default: 1.0).
   # Same as compress_pos_emb.
@@ -154,7 +154,7 @@ draft_model:
 
   # Rope alpha for draft models (default: None).
   # Same as alpha_value. Set to "auto" to auto-calculate.
-  draft_rope_alpha: 
+  draft_rope_alpha:
 
   # Cache mode for draft models to save VRAM (default: FP16).
   # Possible values: 'FP16', 'Q8', 'Q6', 'Q4'.
@@ -169,7 +169,7 @@ lora:
   # For the YAML file, add each entry as a YAML list:
   # - name: lora1
   #   scaling: 1.0
-  loras: 
+  loras:
 
 # Options for embedding models and loading.
 # NOTE: Embeddings requires the "extras" feature to be installed
@@ -185,32 +185,32 @@ embeddings:
   embeddings_device: cpu
 
   # An initial embedding model to load on the infinity backend.
-  embedding_model_name: 
+  embedding_model_name:
 
 # Options for Sampling
 sampling:
   # Select a sampler override preset (default: None).
   # Find this in the sampler-overrides folder.
   # This overrides default fallbacks for sampler values that are passed to the API.
-  override_preset: 
+  override_preset:
 
 # Options for development and experimentation
 developer:
   # Skip Exllamav2 version check (default: False).
   # WARNING: It's highly recommended to update your dependencies rather than enabling this flag.
-  unsafe_launch: False
+  unsafe_launch: false
 
   # Disable API request streaming (default: False).
-  disable_request_streaming: False
+  disable_request_streaming: false
 
   # Enable the torch CUDA malloc backend (default: False).
-  cuda_malloc_backend: False
+  cuda_malloc_backend: false
 
   # Run asyncio using Uvloop or Winloop which can improve performance.
   # NOTE: It's recommended to enable this, but if something breaks turn this off.
-  uvloop: False
+  uvloop: false
 
   # Set process to use a higher priority.
   # For realtime process priority, run as administrator or sudo.
   # Otherwise, the priority will be set to high.
-  realtime_process_priority: False
+  realtime_process_priority: false