> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/mlfoundations/open_clip/llms.txt
> Use this file to discover all available pages before exploring further.

# get_pretrained_cfg

> Get configuration for a specific pretrained model and tag

Retrieves the pretrained configuration dictionary for a specific model architecture and pretrained tag. The configuration includes download URLs, preprocessing parameters, and model-specific settings.

## Signature

```python theme={null}
def get_pretrained_cfg(model: str, tag: str) -> dict:
    ...
```

## Parameters

<ParamField path="model" type="str" required>
  Model architecture name. Must be a valid model from `list_models()`. Examples: `'ViT-B-32'`, `'ViT-L-14'`, `'RN50'`.
</ParamField>

<ParamField path="tag" type="str" required>
  Pretrained weights tag. Must be a valid tag for the specified model. Examples: `'openai'`, `'laion400m_e32'`, `'datacomp_xl_s13b_b90k'`.

  Tag names are case-insensitive and hyphens/underscores are normalized (e.g., `'laion-400m-e32'` and `'laion400m_e32'` are equivalent).
</ParamField>

## Returns

<ResponseField name="config" type="dict">
  Pretrained configuration dictionary containing:

  * `url`: Direct download URL for weights (if available)
  * `hf_hub`: Hugging Face Hub repository path (if available)
  * `mean`: Image normalization mean values (tuple of 3 floats)
  * `std`: Image normalization std values (tuple of 3 floats)
  * `interpolation`: Image interpolation method (`'bicubic'`, `'bilinear'`, etc.)
  * `resize_mode`: Resize strategy (`'shortest'`, `'squash'`, `'longest'`)
  * `quick_gelu`: Whether model uses QuickGELU activation (bool, optional)

  Returns empty dict `{}` if model or tag not found.
</ResponseField>

## Example

```python theme={null}
import open_clip

# Get configuration for OpenAI ViT-B-32
cfg = open_clip.get_pretrained_cfg('ViT-B-32', 'openai')
print(cfg)
# Output:
# {
#     'url': 'https://openaipublic.azureedge.net/clip/models/...',
#     'hf_hub': 'timm/vit_base_patch32_clip_224.openai/',
#     'mean': (0.48145466, 0.4578275, 0.40821073),
#     'std': (0.26862954, 0.26130258, 0.27577711),
#     'interpolation': 'bicubic',
#     'resize_mode': 'shortest',
#     'quick_gelu': True
# }

# Get configuration for LAION ViT-L-14
cfg = open_clip.get_pretrained_cfg('ViT-L-14', 'datacomp_xl_s13b_b90k')
print(f"Download from: {cfg.get('hf_hub', 'N/A')}")
print(f"Interpolation: {cfg['interpolation']}")
print(f"Mean: {cfg['mean']}")
print(f"Std: {cfg['std']}")

# Check if config exists
cfg = open_clip.get_pretrained_cfg('ViT-B-32', 'nonexistent_tag')
if not cfg:
    print("Configuration not found")

# Tag normalization (these are equivalent)
cfg1 = open_clip.get_pretrained_cfg('ViT-B-32', 'laion400m-e32')
cfg2 = open_clip.get_pretrained_cfg('ViT-B-32', 'laion400m_e32')
cfg3 = open_clip.get_pretrained_cfg('ViT-B-32', 'LAION400M-E32')
assert cfg1 == cfg2 == cfg3

# Use config to understand preprocessing requirements
cfg = open_clip.get_pretrained_cfg('ViT-B-16-SigLIP', 'webli')
print(f"SigLIP uses mean: {cfg['mean']}")  # (0.5, 0.5, 0.5)
print(f"SigLIP uses std: {cfg['std']}")    # (0.5, 0.5, 0.5)
print(f"SigLIP resize mode: {cfg['resize_mode']}")  # 'squash'
```

## Configuration Fields

### Download Sources

* **url**: Direct HTTP(S) URL to download weights
* **hf\_hub**: Hugging Face Hub path in format `org/repo/filename` or `org/repo/`

### Preprocessing Parameters

* **mean**: RGB channel means for normalization. Common values:
  * OpenAI/CLIP: `(0.48145466, 0.4578275, 0.40821073)`
  * SigLIP: `(0.5, 0.5, 0.5)`
  * ImageNet: `(0.485, 0.456, 0.406)`

* **std**: RGB channel standard deviations. Common values:
  * OpenAI/CLIP: `(0.26862954, 0.26130258, 0.27577711)`
  * SigLIP: `(0.5, 0.5, 0.5)`
  * ImageNet: `(0.229, 0.224, 0.225)`

* **interpolation**: Resizing interpolation method
  * `'bicubic'`: Higher quality (default for most models)
  * `'bilinear'`: Faster
  * `'nearest'`: Fastest, lowest quality

* **resize\_mode**: How to handle aspect ratios
  * `'shortest'`: Resize shortest edge, center crop (CLIP default)
  * `'squash'`: Resize to exact size, may distort (SigLIP default)
  * `'longest'`: Resize longest edge, center crop

### Model-Specific

* **quick\_gelu**: If True, model uses QuickGELU activation instead of standard GELU

## Helper Functions

```python theme={null}
# Check if a config exists
exists = open_clip.is_pretrained_cfg('ViT-B-32', 'openai')
print(f"Config exists: {exists}")

# Get available tags for a model
tags = open_clip.list_pretrained_tags_by_model('ViT-B-32')
print(f"Available tags: {tags}")

# Get URL only
url = open_clip.get_pretrained_url('ViT-B-32', 'openai')
print(f"Download URL: {url}")
```

## See Also

* [list\_pretrained](/api/list-pretrained) - List all available model/tag combinations
* [list\_pretrained\_tags\_by\_model](/api/list-pretrained) - Get all tags for a specific model
* [create\_model](/api/create-model) - Create a model using these configurations