# InstructBLIP number of parameters

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finstructblip-number-of-parameters%2F51282%3E%5C
**Category:** Intermediate\
**Created:** [August 18, 2023, 9:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finstructblip-number-of-parameters%2F51282 "2023-08-18T21:02:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![nehadhirmiz](https://avatars.discourse-cdn.com/v4/letter/n/3ab097/32.png) [@nehadhirmiz](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnehadhirmiz)%5C
**Post date:** [August 18, 2023, 9:02pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Finstructblip-number-of-parameters%2F51282%2F1 "2023-08-18T21:02:33Z")

</div>

I am loading InstructBLIP based on Vicuna-13B.

```auto
model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-13b", load_in_4bit=True, torch_dtype=torch.bfloat16, cache_dir=download_dir)

```

However, when I print the number of parameters using model.num\_parameters(), I get ~7B parameters. Am I missing something?