update

config.yaml

@@ -3,6 +3,20 @@ model_list:
     litellm_params:
       model: ollama/mistral:7b
       api_base: https://zhengr-ollama.hf.space
+      # Model-specific parameters
+      #model: "huggingface/mistralai/Mistral-7B-Instruct-v0.1" 
+      #api_base: "<your-api-base>"
+      #api_key: "<your-api-key>" # [OPTIONAL] for hf inference endpoints
+      #initial_prompt_value: "\n"
+      #roles: {"system":{"pre_message":"<|im_start|>system\n", "post_message":"<|im_end|>"}, "assistant":{"pre_message":"<|im_start|>assistant\n","post_message":"<|im_end|>"}, "user":{"pre_message":"<|im_start|>user\n","post_message":"<|im_end|>"}}
+      #final_prompt_value: "\n"
+      #bos_token: "<s>"
+      #eos_token: "</s>"
+      #max_tokens: 4096
+  - model_name: xinference-llama-3-instruct
+    litellm_params:
+      model: xinference/llama-3-instruct
+      api_base: https://zhengr-xinference.hf.space
 
 litellm_settings: # module level litellm settings - https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py
   drop_params: True