fix: use correct vLLM model name with hosted_vllm prefix

2025-11-21 19:02:44 +01:00
parent 81d4058c5d
commit fe0cf487ee
1 changed files with 1 additions and 1 deletions
--- a/ai/litellm-config.yaml
+++ b/ai/litellm-config.yaml
@@ -32,7 +32,7 @@ model_list:
  # Text Generation
  - model_name: qwen-2.5-7b
    litellm_params:
-      model: openai/qwen-2.5-7b  # OpenAI-compatible vLLM endpoint
+      model: hosted_vllm/Qwen/Qwen2.5-7B-Instruct  # vLLM HuggingFace model name
      api_base: http://100.121.199.88:9000/v1  # RunPod GPU via Tailscale
      api_key: dummy
      rpm: 1000