backend/space/litellm_config.yaml

litellm_settings:
  drop_params: true
model_list:
  - model_name: 'HuggingFace: Mistral: Mistral 7B Instruct v0.1'
    litellm_params:
      model: huggingface/mistralai/Mistral-7B-Instruct-v0.1
      api_key: os.environ/HF_TOKEN
      max_tokens: 1024
  - model_name: 'HuggingFace: Mistral: Mistral 7B Instruct v0.2'
    litellm_params:
      model: huggingface/mistralai/Mistral-7B-Instruct-v0.2
      api_key: os.environ/HF_TOKEN
      max_tokens: 1024
  - model_name: 'HuggingFace: Meta: Llama 3 8B Instruct'
    litellm_params:
      model: huggingface/meta-llama/Meta-Llama-3-8B-Instruct
      api_key: os.environ/HF_TOKEN
      max_tokens: 2047
  - model_name: 'HuggingFace: Mistral: Mixtral 8x7B Instruct v0.1'
    litellm_params:
      model: huggingface/mistralai/Mixtral-8x7B-Instruct-v0.1
      api_key: os.environ/HF_TOKEN
      max_tokens: 8192
  - model_name: 'HuggingFace: Microsoft: Phi-3 Mini-4K-Instruct'
    litellm_params:
      model: huggingface/microsoft/Phi-3-mini-4k-instruct
      api_key: os.environ/HF_TOKEN
      max_tokens: 1024
  - model_name: 'HuggingFace: Google: Gemma 7B 1.1'
    litellm_params:
      model: huggingface/google/gemma-1.1-7b-it
      api_key: os.environ/HF_TOKEN
      max_tokens: 1024
  - model_name: 'HuggingFace: Yi-1.5 34B Chat'
    litellm_params:
      model: huggingface/01-ai/Yi-1.5-34B-Chat
      api_key: os.environ/HF_TOKEN
      max_tokens: 1024
  - model_name: 'HuggingFace: Nous Research: Nous Hermes 2 Mixtral 8x7B DPO'
    litellm_params:
      model: huggingface/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
      api_key: os.environ/HF_TOKEN
      max_tokens: 2048