Try using Qwen/Qwen2.5-Coder-1.5B-Instruct

Signed-off-by: Radoslav Dimitrov <[email protected]>

Author: rdimitrov

.github/workflows/integration-tests.yml

@@ -153,7 +153,7 @@ jobs:
           docker build -f Dockerfile.cpu -t vllm-cpu-env --shm-size=4g .
           docker run -d  --name vllm \
              --network="host" \
-             vllm-cpu-env --model Qwen/Qwen2.5-Coder-0.5B-Instruct
+             vllm-cpu-env --model Qwen/Qwen2.5-Coder-1.5B-Instruct
 
       - name: Verify the vllm container is running
         run: |
@@ -169,7 +169,7 @@ jobs:
 
           echo -e "\nVerify the completions endpoint works\n"
           curl http://localhost:8000/v1/completions -H "Content-Type: application/json"   -d '{
-              "model": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
+              "model": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
               "prompt": ["How to make pizza"],
               "max_tokens": 100,
               "temperature": 0
@@ -179,7 +179,7 @@ jobs:
           curl -X POST http://localhost:8000/v1/chat/completions \
               -H "Content-Type: application/json" \
               -d '{
-                "model": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
+                "model": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
                 "messages": [
                   {"role": "system", "content": "You are a coding assistant."},
                   {"role": "user", "content": "Hello"}

tests/integration/testcases.yaml

@@ -160,7 +160,7 @@ testcases:
               "role":"user"
             }
         ],
-        "model":"Qwen/Qwen2.5-Coder-0.5B-Instruct",
+        "model":"Qwen/Qwen2.5-Coder-1.5B-Instruct",
         "stream":true,
         "temperature":0
       }
@@ -173,7 +173,7 @@ testcases:
     url: http://127.0.0.1:8989/vllm/completions
     data: |
       {
-        "model": "Qwen/Qwen2.5-Coder-0.5B-Instruct",
+        "model": "Qwen/Qwen2.5-Coder-1.5B-Instruct",
         "max_tokens": 4096,
         "temperature": 0,
         "stream": true,