PythiaModel class
Constructors
- PythiaModel(PythiaConfig config)
Properties
-
blocks
→ List<
PythiaBlock> -
final
- config → PythiaConfig
-
final
- embedIn → Embedding
-
final
- embedOut → Linear
-
final
- finalLn → LayerNorm
-
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- rope → RopeCache
-
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- training ↔ bool
-
Whether this module is in training mode. Layers that behave
differently between training and inference (e.g.
Dropout) read this flag in theircallmethod. Defaults to training mode.getter/setter pairinherited
Methods
-
call(
Tensor tokens) → Tensor -
Forward pass.
tokensis a 1D[seqLen]tensor of class indices as float32 (matches GPT). Output is[seqLen, vocab]. -
eval(
) → void -
Put this module (and any registered submodules) into evaluation mode.
inherited
-
generate(
List< double> prompt, {required int maxNewTokens, double temperature = 1.0, int? topK, Random? rng, bool useCache = true}) → List<double> -
Autoregressive sampling. Same signature and behaviour as
GPT.generate. -
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
parameters(
) → List< Tensor> -
Trainable tensors owned by this module (and its submodules).
override
-
submodules(
) → List< Module> -
Submodules owned by this module. Subclasses that compose other
modules should override this so
train()/eval()propagate. Default: empty.override -
toString(
) → String -
A string representation of this object.
inherited
-
train(
) → void -
Put this module (and any registered submodules) into training mode.
inherited
-
zeroGrad(
) → void -
Zero every parameter's gradient. Safe to call before each
backward.inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited