LLamaSharp

333 MB

Tree: 6f9097f25b

Author	SHA1	Message	Date
Martin Evans	835958398c	- Removed the object wrappers and configurable pipeline, they can be better written in code. - Added BaseSamplingPipeline which provides a base impl of `ISamplingPipeline` - Added `DefaultSamplingPipeline` which mimics normal llama.cpp sampling	1 year ago
Martin Evans	45118520fa	- Improved coverage of `GBNFGrammarParser` up to 96% - Covered text transforms - Removed unnecessary non-async transforms	2 years ago
Martin Evans	9f694c584c	Further improved grammar parser test coverage (up to 92%)	2 years ago
Martin Evans	bff41eef37	Added some more coverage of `GrammarRule`, checking that invalid rules are rejected	2 years ago
Martin Evans	a70c7170dd	- Created a higher level `Grammar` class which is immutable and contains a list of grammar rules. This is the main "entry point" to the grammar system. - Made all the mechanics of grammar parsing (GBNFGrammarParser, ParseState) internal. Just call `Grammar.Parse("whatever")`. - Added a `GrammarRule` class which validates elements on construction (this allows constructing grammar without parsing GBNF). - It should be impossible for a `GrammarRule` to represent an invalid rule.	2 years ago
Mihai	920efaca44	Add original test	2 years ago
Mihai	2ae1891c13	Bug fixes after running tests. SymbolIds is now SortedDictionary (although I'm not sure it really needs to be) because the test was failing due to expected value being in another order. The C++ data structure if SymbolIds is std::map<std::string, uint32_t> so the items are ordered by key.	2 years ago
Mihai	0bd495276b	Add initial tests + fix bugs. Still WIP since the test is failing.	2 years ago

8 Commits (6f9097f25bdb9726335a2aecf1f087cc6e2a4990)