Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Feb 16, 2025
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d102707
update doc
ywang96 Feb 16, 2025
a4f79c0
update examples
ywang96 Feb 16, 2025
9506bd9
update
ywang96 Feb 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/source/models/supported_models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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}
Expand Down
4 changes: 2 additions & 2 deletions examples/offline_inference/vision_language.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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,
Expand All @@ -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

Expand Down
5 changes: 2 additions & 3 deletions examples/offline_inference/vision_language_multi_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand All @@ -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(
Expand Down