generation/logits_sampler

• generation/logits_sampler
  • static
    • .LogitsSampler
      • new LogitsSampler(generation_config)
      • instance
        • ._call(logits) ⇒ *
        • .sample(logits) ⇒ *
        • .getLogits(logits, index) ⇒ Float32Array
        • .randomSelect(probabilities) ⇒ number
      • static
        • .getSampler(generation_config) ⇒ LogitsSampler
  • inner
    • ~GreedySampler
      • .sample(logits) ⇒ *
    • ~MultinomialSampler
      • .sample(logits) ⇒ *
    • ~BeamSearchSampler
      • .sample(logits) ⇒ *

---

generation/logits_sampler.LogitsSampler

Sampler is a base class for all sampling methods used for text generation.

Kind: static class of generation/logits_sampler

• .LogitsSampler
  • new LogitsSampler(generation_config)
  • instance
    • ._call(logits) ⇒ *
    • .sample(logits) ⇒ *
    • .getLogits(logits, index) ⇒ Float32Array
    • .randomSelect(probabilities) ⇒ number
  • static
    • .getSampler(generation_config) ⇒ LogitsSampler

---

new LogitsSampler(generation_config)

Creates a new Sampler object with the specified generation config.

Param	Type	Description
generation_config	GenerationConfig	The generation config.

---

logitsSampler._call(logits) ⇒ <code> * </code>

Executes the sampler, using the specified logits.

Kind: instance method of LogitsSampler

Param	Type
logits	Tensor

---

logitsSampler.sample(logits) ⇒ <code> * </code>

Abstract method for sampling the logits.

Kind: instance method of LogitsSampler
Throws:

• Error If not implemented in subclass.

Param	Type
logits	Tensor

---

logitsSampler.getLogits(logits, index) ⇒ <code> Float32Array </code>

Returns the specified logits as an array, with temperature applied.

Kind: instance method of LogitsSampler

Param	Type
logits	Tensor
index	number

---

logitsSampler.randomSelect(probabilities) ⇒ <code> number </code>

Selects an item randomly based on the specified probabilities.

Kind: instance method of LogitsSampler
Returns: number - The index of the selected item.

Param	Type	Description
probabilities	*	An array of probabilities to use for selection.

---

LogitsSampler.getSampler(generation_config) ⇒ <code> LogitsSampler </code>

Returns a Sampler object based on the specified options.

Kind: static method of LogitsSampler
Returns: LogitsSampler - A Sampler object.

Param	Type	Description
generation_config	GenerationConfig	An object containing options for the sampler.

---

generation/logits_sampler~GreedySampler

Class representing a Greedy Sampler.

Kind: inner class of generation/logits_sampler

---

greedySampler.sample(logits) ⇒ <code> * </code>

Sample the maximum probability of a given logits tensor.

Kind: instance method of GreedySampler
Returns: * - An array with a single tuple, containing the index of the maximum value and a meaningless score (since this is a greedy search).

Param	Type
logits	Tensor

---

generation/logits_sampler~MultinomialSampler

Class representing a MultinomialSampler.

Kind: inner class of generation/logits_sampler

---

multinomialSampler.sample(logits) ⇒ <code> * </code>

Sample from the logits.

Kind: instance method of MultinomialSampler

Param	Type
logits	Tensor

---

generation/logits_sampler~BeamSearchSampler

Class representing a BeamSearchSampler.

Kind: inner class of generation/logits_sampler

---

beamSearchSampler.sample(logits) ⇒ <code> * </code>

Sample from the logits.

Kind: instance method of BeamSearchSampler

Param	Type
logits	Tensor

---

< > Update on GitHub