|
ember.cpp 0.1.0
C++ inference engine for Llama-family and paperkiln models (CPU, CUDA, WebAssembly)
|
This is the complete list of members for microtorch::llama3::Tokenizer, including all inherited members.
| decode(const std::vector< int > &ids) const | microtorch::llama3::Tokenizer | inline |
| encode(const std::string &text) const | microtorch::llama3::Tokenizer | inline |
| encode_word(const std::string &word, std::vector< int > &out) const | microtorch::llama3::Tokenizer | inlineprivate |
| id_ | microtorch::llama3::Tokenizer | private |
| max_digits_ | microtorch::llama3::Tokenizer | private |
| rank_ | microtorch::llama3::Tokenizer | private |
| size() const | microtorch::llama3::Tokenizer | inline |
| special_ | microtorch::llama3::Tokenizer | private |
| specials_ | microtorch::llama3::Tokenizer | private |
| Tokenizer(std::vector< std::string > tokens, const std::vector< std::string > &merges, const std::vector< int32_t > &token_type, size_t max_digits=3) | microtorch::llama3::Tokenizer | inline |
| tokens() const | microtorch::llama3::Tokenizer | inline |
| tokens_ | microtorch::llama3::Tokenizer | private |
| unbyte_ | microtorch::llama3::Tokenizer | private |
| utf8_len(unsigned char c) | microtorch::llama3::Tokenizer | inlineprivatestatic |