> ## 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.

# create_model

> Creates and configures a contrastive vision-language model

Creates and configures a contrastive vision-language model with flexible weight loading options.

## Signature

```python theme={null}
def create_model(
    model_name: str,
    pretrained: Optional[str] = None,
    load_weights: bool = True,
    precision: str = 'fp32',
    device: Union[str, torch.device] = 'cpu',
    jit: bool = False,
    force_quick_gelu: bool = False,
    force_custom_text: bool = False,
    force_patch_dropout: Optional[float] = None,
    force_image_size: Optional[Union[int, Tuple[int, int]]] = None,
    force_preprocess_cfg: Optional[Dict[str, Any]] = None,
    force_context_length: Optional[int] = None,
    pretrained_image: bool = False,
    pretrained_text: bool = True,
    pretrained_image_path: Optional[str] = None,
    pretrained_text_path: Optional[str] = None,
    cache_dir: Optional[str] = None,
    output_dict: Optional[bool] = None,
    require_pretrained: bool = False,
    weights_only: bool = True,
    **model_kwargs,
) -> torch.nn.Module:
    ...
```

## Parameters

<ParamField path="model_name" type="str" required>
  Model identifier, potentially with schema prefix:

  * `'ViT-B-32'`: Built-in model name. `pretrained` specifies CLIP weights source (tag or file path).
  * `'hf-hub:org/repo'`: Loads config/weights from HuggingFace Hub. `pretrained` is IGNORED.
  * `'local-dir:/path/to/folder'`: Loads config/weights from local directory. `pretrained` is IGNORED.
</ParamField>

<ParamField path="pretrained" type="Optional[str]" default="None">
  Source for CLIP weights (tag or file path) ONLY if `model_name` has no schema. Can be a pretrained tag like `'openai'`, `'laion400m_e32'`, or a path to a checkpoint file.
</ParamField>

<ParamField path="load_weights" type="bool" default="True">
  Load the resolved pretrained weights if True, otherwise random init or tower overrides only.
</ParamField>

<ParamField path="precision" type="str" default="'fp32'">
  Model precision. Options: `'fp32'`, `'fp16'`, `'bf16'`, `'pure_fp16'`, `'pure_bf16'`.
</ParamField>

<ParamField path="device" type="Union[str, torch.device]" default="'cpu'">
  Device to load model on. Can be `'cpu'`, `'cuda'`, or a torch.device object.
</ParamField>

<ParamField path="jit" type="bool" default="False">
  If True, JIT compile the model using torch.jit.script.
</ParamField>

<ParamField path="force_quick_gelu" type="bool" default="False">
  Force use of QuickGELU activation in model config instead of standard GELU.
</ParamField>

<ParamField path="force_custom_text" type="bool" default="False">
  Force use of custom text encoder architecture (CustomTextCLIP).
</ParamField>

<ParamField path="force_patch_dropout" type="Optional[float]" default="None">
  Override patch dropout value in model config. Values typically range from 0.0 to 1.0.
</ParamField>

<ParamField path="force_image_size" type="Optional[Union[int, Tuple[int, int]]]" default="None">
  Override image size in model config. Can be a single int (square) or tuple (height, width).
</ParamField>

<ParamField path="force_preprocess_cfg" type="Optional[Dict[str, Any]]" default="None">
  Dictionary to override specific preprocessing parameters (mean, std, interpolation, resize\_mode).
</ParamField>

<ParamField path="force_context_length" type="Optional[int]" default="None">
  Override context length (max sequence length) in text config.
</ParamField>

<ParamField path="pretrained_image" type="bool" default="False">
  Load default base weights for image tower at creation if no CLIP weights loaded. Only effective for timm-based vision models.
</ParamField>

<ParamField path="pretrained_text" type="bool" default="True">
  Load default base weights for text tower at creation if no CLIP weights loaded. Only effective for HuggingFace-based text models.
</ParamField>

<ParamField path="pretrained_image_path" type="Optional[str]" default="None">
  Path to load weights specifically into image tower after model creation. Loads after full CLIP checkpoint.
</ParamField>

<ParamField path="pretrained_text_path" type="Optional[str]" default="None">
  Path to load weights specifically into text tower after model creation. Loads after full CLIP checkpoint.
</ParamField>

<ParamField path="cache_dir" type="Optional[str]" default="None">
  Cache directory for downloaded weights. Defaults to `~/.cache/clip`.
</ParamField>

<ParamField path="output_dict" type="Optional[bool]" default="None">
  If True and model supports it, return dictionary output instead of tensors.
</ParamField>

<ParamField path="require_pretrained" type="bool" default="False">
  Raise error if no pretrained CLIP weights loaded when required.
</ParamField>

<ParamField path="weights_only" type="bool" default="True">
  Use weights\_only=True for torch.load (safer, prevents arbitrary code execution).
</ParamField>

<ParamField path="**model_kwargs" type="Any">
  Additional keyword arguments for model constructor (highest override priority).
</ParamField>

## Returns

<ResponseField name="model" type="torch.nn.Module">
  The created model instance (CLIP, CustomTextCLIP, or CoCa depending on configuration).
</ResponseField>

## Example

```python theme={null}
import open_clip

# Create model with OpenAI pretrained weights
model = open_clip.create_model('ViT-B-32', pretrained='openai')

# Create model from HuggingFace Hub
model = open_clip.create_model('hf-hub:laion/CLIP-ViT-L-14-DataComp.XL-s13B-b90K')

# Create model with custom image size
model = open_clip.create_model(
    'ViT-L-14',
    pretrained='datacomp_xl_s13b_b90k',
    force_image_size=336,
    device='cuda',
    precision='fp16'
)

# Create model from local directory
model = open_clip.create_model('local-dir:/path/to/model')

# Create model with separate tower weights
model = open_clip.create_model(
    'ViT-B-32',
    pretrained_image_path='/path/to/image_weights.pt',
    pretrained_text_path='/path/to/text_weights.pt'
)
```