---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
library_name: nanovlm
license: mit
pipeline_tag: image-text-to-text
tags:
  - vision-language
  - multimodal
  - research
---

**Usage:**

Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM.
Follow the install instructions and run the following code:

```python
from models.vision_language_model import VisionLanguageModel

model = VisionLanguageModel.from_pretrained("lusxvr/nanoVLM-230M-8k-2")
```

```
"results": {
        "docvqa_val_anls": 0.772357483001645,
        "docvqa_val_anls_stderr": 0.005426685320059236,
        "infovqa_val_anls": 0.27699762812164563,
        "infovqa_val_anls_stderr": 0.007008485987608615,
        "mme_mme_cognition_score": 242.85714285714286,
        "mme_mme_perception_score": 1132.1020408163265,
        "mmmu_val_mmmu_acc": 0.29889,
        "mmstar_coarse perception": 0.48384750306507346,
        "mmstar_average": 0.36924953254941295,
        "mmstar_fine-grained perception": 0.36457258658806185,
        "mmstar_instance reasoning": 0.344255653063192,
        "mmstar_logical reasoning": 0.34837483748374837,
        "mmstar_math": 0.390821304464047,
        "mmstar_science & technology": 0.283625310632355,
        "ocrbench_ocrbench_accuracy": 0.727,
        "scienceqa_exact_match": 0.5868898844612119,
        "scienceqa_exact_match_stderr": 0.0075618541822843575,
        "textvqa_val_exact_match": 0.59624,
        "textvqa_val_exact_match_stderr": 0.006634483834869976,
        "chartqa_relaxed_overall": 0.732,
        "chartqa_relaxed_overall_stderr": 0.008860124193276758,
        "chartqa_relaxed_human_split": 0.544,
        "chartqa_relaxed_human_split_stderr": 0.014092909141495816,
        "chartqa_relaxed_augmented_split": 0.92,
        "chartqa_relaxed_augmented_split_stderr": 0.007676401612303169,
        "ai2d_exact_match": 0.41547927461139894,
        "ai2d_exact_match_stderr": 0.008869646776634895,
        "mathvista_testmini_cot_gpt_eval_score": 32.1,
        "mathvista_testmini_format_gpt_eval_score": 36.7,
        "mathvista_testmini_solution_gpt_eval_score": 32.7
    }
```