jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Config: Default None -> Empty in comments

Browse source 
Empty makes more sense when talking about empty fields.

Signed-off-by: kingbri <bdashore3@proton.me>
This commit is contained in:
kingbri 2023-12-28 00:32:29 -05:00
parent f56221ff0c
commit c72d30918c
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
config_sample.yml
View file

@ -42,11 +42,11 @@ model:
# The below parameters apply only if model_name is set
# Max sequence length (default: None)
# Max sequence length (default: Empty)
# Fetched from the model's base sequence length in config.json by default
max_seq_len:
# Overrides base model context length (default: None)
# Overrides base model context length (default: Empty)
# 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:
@ -73,11 +73,11 @@ model:
# 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)
# Set the prompt template for this model. If empty, chat completions will be disabled. (default: Empty)
# NOTE: Only works with chat completion message lists!
prompt_template:
# Number of experts to use PER TOKEN. Fetched from the model's config.json if not specified (default: None)
# Number of experts to use PER TOKEN. Fetched from the model's config.json if not specified (default: Empty)
# WARNING: Don't set this unless you know what you're doing!
# NOTE: For MoE models (ex. Mixtral) only!
num_experts_per_token: