[Model] support Qianfan-OCR model (#40136)

Signed-off-by: bairongz <baiyuu.cs@gmail.com>
Signed-off-by: zhuangbairong <zhuangbairong@baidu.com>
Co-authored-by: zhuangbairong <zhuangbairong@baidu.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
bairongz
2026-05-05 10:51:25 +00:00
committed by GitHub
co-authored by zhuangbairong gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 8b9ea2f881
commit 0a201b60cf
9 changed files with 312 additions and 0 deletions
@@ -928,6 +928,16 @@ VLM_TEST_SETTINGS = {
),
],
),
"qianfan_ocr": VLMTestInfo(
models=["baidu/Qianfan-OCR"],
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),
prompt_formatter=lambda img_prompt: f"<|im_start|>user\n{img_prompt}<|im_end|>\n<|im_start|>assistant\n", # noqa: E501
img_idx_to_prompt=lambda idx: "<image>",
max_model_len=4096,
use_tokenizer_eos=True,
auto_cls=AutoModelForImageTextToText,
hf_model_kwargs=model_utils.qianfan_ocr_hf_model_kwargs("baidu/Qianfan-OCR"),
),
"qwen_vl": VLMTestInfo(
models=["Qwen/Qwen-VL"],
test_type=(VLMTestType.IMAGE, VLMTestType.MULTI_IMAGE),