youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[MODEL ADDITION] Ovis2 Model Addition (#15826)

Browse Source 
Signed-off-by: Marco <121761685+mlinmg@users.noreply.github.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Marco
2025-04-30 09:33:29 +02:00
committed by GitHub
parent be633fba0f
commit 54072f315f
17 changed files with 1349 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
examples/offline_inference/vision_language_multi_image.py
View File

@ -436,6 +436,36 @@ def load_nvlm_d(question: str, image_urls: list[str]) -> ModelRequestData:
)
# Ovis2
def load_ovis2(question: str, image_urls: list[str]) -> ModelRequestData:
model_name = "AIDC-AI/Ovis2-1B"
tokenizer = "Isotr0py/Ovis2-tokenizer"
engine_args = EngineArgs(
model=model_name,
tokenizer=tokenizer,
max_model_len=8192,
max_num_seqs=2,
trust_remote_code=True,
dtype="half",
limit_mm_per_prompt={"image": len(image_urls)},
hf_overrides={"architectures": ["Ovis2ForConditionalGeneration"]},
)
placeholder = '\n'.join(
[f'Image {i+1}: <image>' for i in range(len(image_urls))]) + '\n'
prompt = ("<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"
f"<|im_start|>user\n{placeholder}"
f"{question}<|im_end|>\n"
"<|im_start|>assistant\n")
return ModelRequestData(
engine_args=engine_args,
prompt=prompt,
image_data=[fetch_image(url) for url in image_urls],
)
def load_pixtral_hf(question: str, image_urls: list[str]) -> ModelRequestData:
model_name = "mistral-community/pixtral-12b"
@ -685,6 +715,7 @@ model_example_map = {
"mistral3": load_mistral3,
"mllama": load_mllama,
"NVLM_D": load_nvlm_d,
"ovis2": load_ovis2,
"phi3_v": load_phi3v,
"phi4_mm": load_phi4mm,
"pixtral_hf": load_pixtral_hf,