forked from phoenix/litellm-mirror
34 lines
No EOL
2.2 KiB
TOML
34 lines
No EOL
2.2 KiB
TOML
[keys]
|
|
# HUGGINGFACE_API_KEY="" # Uncomment to save your Hugging Face API key
|
|
# OPENAI_API_KEY="" # Uncomment to save your OpenAI API Key
|
|
# TOGETHERAI_API_KEY="" # Uncomment to save your TogetherAI API key
|
|
# NLP_CLOUD_API_KEY="" # Uncomment to save your NLP Cloud API key
|
|
# ANTHROPIC_API_KEY="" # Uncomment to save your Anthropic API key
|
|
# REPLICATE_API_KEY="" # Uncomment to save your Replicate API key
|
|
# AWS_ACCESS_KEY_ID = "" # Uncomment to save your Bedrock/Sagemaker access keys
|
|
# AWS_SECRET_ACCESS_KEY = "" # Uncomment to save your Bedrock/Sagemaker access keys
|
|
|
|
[general]
|
|
# add_function_to_prompt = true # e.g: Ollama doesn't support functions, so add it to the prompt instead
|
|
# drop_params = true # drop any params not supported by the provider (e.g. Ollama)
|
|
# default_model = None # route all requests to this model
|
|
# local_logging = true # writes logs to a local 'api_log.json' file for debugging
|
|
# fallbacks = ["gpt-3.5-turbo", "gpt-4"] # models you want to fallback to in case completion call fails (remember: add relevant keys)
|
|
|
|
[model."ollama/llama2"] # run via `litellm --model ollama/llama2`
|
|
# max_tokens = "" # set max tokens for the model
|
|
# temperature = "" # set temperature for the model
|
|
# api_base = "" # set a custom api base for the model
|
|
|
|
[model."ollama/llama2".prompt_template] # [OPTIONAL] LiteLLM can automatically formats the prompt - docs: https://docs.litellm.ai/docs/completion/prompt_formatting
|
|
# MODEL_SYSTEM_MESSAGE_START_TOKEN = "[INST] <<SYS>>\n" # This does not need to be a token, can be any string
|
|
# MODEL_SYSTEM_MESSAGE_END_TOKEN = "\n<</SYS>>\n [/INST]\n" # This does not need to be a token, can be any string
|
|
|
|
# MODEL_USER_MESSAGE_START_TOKEN = "[INST] " # This does not need to be a token, can be any string
|
|
# MODEL_USER_MESSAGE_END_TOKEN = " [/INST]\n" # Applies only to user messages. Can be any string.
|
|
|
|
# MODEL_ASSISTANT_MESSAGE_START_TOKEN = "" # Applies only to assistant messages. Can be any string.
|
|
# MODEL_ASSISTANT_MESSAGE_END_TOKEN = "\n" # Applies only to system messages. Can be any string.
|
|
|
|
# MODEL_PRE_PROMPT = "You are a good bot" # Applied at the start of the prompt
|
|
# MODEL_POST_PROMPT = "Now answer as best as you can" # Applied at the end of the prompt |