Uses of Interface
io.github.kirstenali.deepj.tokenizers.Tokenizer
Packages that use Tokenizer
Package
Description
-
Uses of Tokenizer in io.github.kirstenali.deepj.data
Methods in io.github.kirstenali.deepj.data with parameters of type TokenizerModifier and TypeMethodDescriptionstatic TextDatasetStream-tokenize a text file and memory-map the result.Constructors in io.github.kirstenali.deepj.data with parameters of type TokenizerModifierConstructorDescriptionRandomAccessTextDataset(Path path, Tokenizer tokenizer, int seqLen, long seed) -
Uses of Tokenizer in io.github.kirstenali.deepj.models
Methods in io.github.kirstenali.deepj.models with parameters of type TokenizerModifier and TypeMethodDescriptionstatic StringTextGenerator.generate(DeepSeekModel model, Tokenizer tok, TransformerConfig cfg, String prompt, int maxNewTokens, float temperature, int topK, long seed) static StringTextGenerator.generate(GPTModel model, Tokenizer tok, GPTConfig cfg, String prompt, int maxNewTokens, float temperature, int topK, long seed) static StringTextGenerator.generate(LlamaModel model, Tokenizer tok, TransformerConfig cfg, String prompt, int maxNewTokens, float temperature, int topK, long seed) static StringTextGenerator.generate(Function<int[], Tensor> forwarder, int maxSeqLen, Tokenizer tok, String prompt, int maxNewTokens, float temperature, int topK, long seed) Generate text with an explicitmaxSeqLen— useful when no config is available.static StringTextGenerator.generate(Function<int[], Tensor> forwarder, TransformerConfig cfg, Tokenizer tok, String prompt, int maxNewTokens, float temperature, int topK, long seed) Generate text using any model that mapsint[] ids → [seqLen × vocabSize]logits. -
Uses of Tokenizer in io.github.kirstenali.deepj.tokenizers
Classes in io.github.kirstenali.deepj.tokenizers that implement TokenizerModifier and TypeClassDescriptionfinal classMinimal byte-level tokenizers (0-255). -
Uses of Tokenizer in io.github.kirstenali.deepj.tokenizers.bpe
Classes in io.github.kirstenali.deepj.tokenizers.bpe that implement Tokenizer