[V1] Update doc and examples for H2O-VL (#13349)

Signed-off-by: Roger Wang <[email protected]>

Author: ywang96

docs/source/models/supported_models.md

@@ -726,7 +726,7 @@ See [this page](#generative-models) for more information on how to use generativ
   * `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc.
   *
   * ✅︎
-  * \*
+  * ✅︎\*
 - * `Idefics3ForConditionalGeneration`
   * Idefics3
   * T + I
@@ -869,7 +869,7 @@ See [this page](#generative-models) for more information on how to use generativ
 <sup>+</sup> Multiple items can be inputted per text prompt for this modality.
 
 :::{note}
-H2O-VL series models will be available in V1 once we support backends other than FlashAttention.
+`h2oai/h2ovl-mississippi-2b` will be available in V1 once we support backends other than FlashAttention.
 :::
 
 :::{note}

examples/offline_inference/vision_language.py

@@ -119,7 +119,7 @@ def run_glm4v(question: str, modality: str):
 def run_h2ovl(question: str, modality: str):
     assert modality == "image"
 
-    model_name = "h2oai/h2ovl-mississippi-2b"
+    model_name = "h2oai/h2ovl-mississippi-800m"
 
     llm = LLM(
         model=model_name,
@@ -136,7 +136,7 @@ def run_h2ovl(question: str, modality: str):
                                            add_generation_prompt=True)
 
     # Stop tokens for H2OVL-Mississippi
-    # https://huggingface.co/h2oai/h2ovl-mississippi-2b
+    # https://huggingface.co/h2oai/h2ovl-mississippi-800m
     stop_token_ids = [tokenizer.eos_token_id]
     return llm, prompt, stop_token_ids
 

examples/offline_inference/vision_language_multi_image.py

@@ -78,14 +78,13 @@ def load_deepseek_vl2(question: str, image_urls: List[str]):
 
 
 def load_h2ovl(question: str, image_urls: List[str]) -> ModelRequestData:
-    model_name = "h2oai/h2ovl-mississippi-2b"
+    model_name = "h2oai/h2ovl-mississippi-800m"
 
     llm = LLM(
         model=model_name,
         trust_remote_code=True,
         max_model_len=8192,
         limit_mm_per_prompt={"image": len(image_urls)},
-        mm_processor_kwargs={"max_dynamic_patch": 4},
     )
 
     placeholders = "\n".join(f"Image-{i}: <image>\n"
@@ -99,7 +98,7 @@ def load_h2ovl(question: str, image_urls: List[str]) -> ModelRequestData:
                                            add_generation_prompt=True)
 
     # Stop tokens for H2OVL-Mississippi
-    # https://huggingface.co/h2oai/h2ovl-mississippi-2b
+    # https://huggingface.co/h2oai/h2ovl-mississippi-800m
     stop_token_ids = [tokenizer.eos_token_id]
 
     return ModelRequestData(