[Model] Initialize support for InternVL2 series models (#6514)

Co-authored-by: Roger Wang <ywang@roblox.com>

examples/offline_inference_vision_language.py

@@ -106,6 +106,20 @@ def run_minicpmv(question):
     return llm, prompt
 
 
+# InternVL
+def run_internvl(question):
+    # Generally, InternVL can use chatml template for conversation
+    TEMPLATE = "<|im_start|>User\n{prompt}<|im_end|>\n<|im_start|>Assistant\n"
+    prompt = f"<image>\n{question}\n"
+    prompt = TEMPLATE.format(prompt=prompt)
+    llm = LLM(
+        model="OpenGVLab/InternVL2-4B",
+        trust_remote_code=True,
+        max_num_seqs=5,
+    )
+    return llm, prompt
+
+
 # BLIP-2
 def run_blip2(question):
 
@@ -125,6 +139,7 @@ model_example_map = {
     "chameleon": run_chameleon,
     "minicpmv": run_minicpmv,
     "blip-2": run_blip2,
+    "internvl_chat": run_internvl,
 }
 
 

examples/openai_vision_api_client.py

@@ -42,6 +42,7 @@ chat_completion_from_url = client.chat.completions.create(
         ],
     }],
     model=model,
+    max_tokens=64,
 )
 
 result = chat_completion_from_url.choices[0].message.content
@@ -78,6 +79,7 @@ chat_completion_from_base64 = client.chat.completions.create(
         ],
     }],
     model=model,
+    max_tokens=64,
 )
 
 result = chat_completion_from_base64.choices[0].message.content