WeightExportGuide class

Utility for converting PyTorch/HuggingFace model weights to a format suitable for the Dart Donut model.

Use this with a Python script to export weights:

import torch, json, base64
from safetensors.torch import load_file

weights = load_file("model.safetensors")
out = {}
for name, tensor in weights.items():
    t = tensor.cpu().float().numpy()
    out[name] = {
        "shape": list(t.shape),
        "dtype": "float32",
        "data": base64.b64encode(t.tobytes()).decode()
    }
with open("weights.json", "w") as f:
    json.dump(out, f)

Constructors

WeightExportGuide()

Properties

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Constants

exportScript → const String

Python script to convert HuggingFace model to JSON weights.

tokenizerExportScript → const String

Python script to export tokenizer in HuggingFace format.