48 Commits (43677c511c68f69d264e16f3ae6bf7e7f5fc4d5f)

Author SHA1 Message Date
  SignalRT 43677c511c Change interface to support multiple images and add the capabitlity to render the image in the console 1 year ago
  SignalRT e8732efadd Example InteractiveExecutor 1 year ago
  eublefar af796fc3e9 Change List types in executor state to arrays to enforce copy on get/set operations 1 year ago
  eublefar e05d5d4e14 Remove resetting state ops and make SessionState.ExecutorState and SessionState.ContextState no nullable 1 year ago
  eublefar 35153a77dd Chat session Get/Load in-memory state operations, reset state ops for stateful executors and context 1 year ago
  Martin Evans 8ac1634233
Removed `llama_eval`. It is going to be completely removed in the next version of llama.cpp (#553) 1 year ago
  Martin Evans c7d0dc915a Assorted small changes to clean up some code warnings 1 year ago
  Martin Evans b0acecf080 Created a new `BatchedExecutor` which processes multiple "Conversations" in one single inference batch. This is faster, even when the conversations are unrelated, and is much faster if the conversations share some overlap (e.g. a common system prompt prefix). 1 year ago
  Martin Evans 15a98b36d8 Updated everything to work with llama.cpp ce32060198 1 year ago
  Martin Evans a2e29d393c Swapped `StatelessExecutor` to use `llama_decode`! 1 year ago
  Martin Evans 42be9b136d Switched form using raw integers, to a `LLamaToken` struct 1 year ago
  Martin Evans b34f72a883 - Added `SamplingPipeline` to inference params which overrides all other options with an entirely custom pipeline. 1 year ago
  Martin Evans 48c5039054 Improved test coverage. Discovered some issues: 2 years ago
  Martin Evans d743516070 - Added support for the MinP sampler 2 years ago
  Martin Evans a024d2242e It works! 2 years ago
  Martin Evans f1e5a8f995 - Passing the `ILogger` through to every call of `CreateContext` 2 years ago
  sa_ddam213 4ec9aed47a
Revert LLamasSharp project changes 2 years ago
  sa_ddam213 9b8de007dc Propagate ILogger 2 years ago
  Martin Evans 3f80190f85 Minimal changes required to remove non-async inference. 2 years ago
  Martin Evans a09aa86324
Merge pull request #153 from martindevans/fix_savestate_OpenOrCreate 2 years ago
  Martin Evans f366aa3abe Changed `OpenOrCreate` to `Create` to fix #151 2 years ago
  Martin Evans 77bd090150 Simplified `LLamaInteractExecutor` antiprompt matching by using new extension method 2 years ago
  Martin Evans 33035c82bf - Removed `LLamaNewlineTokens` from `InteractiveExecutorState`. This is always set in the constructor from the context, so there's no point serializing it. 2 years ago
  sa_ddam213 a5d742b72c
Fix Tokenize of new line, Remove space inserts 2 years ago
  Martin Evans 31287b5e6e Rewritten TokenToSpan/TokenToString to better fit the new way it's done in llama.cpp with a few different options: 2 years ago
  Martin Evans 0c98ae1955 Passing ctx to `llama_token_nl(_ctx)` 2 years ago
  Martin Evans 829f32b27d - Added `Obsolete` attributes to the entire `OldVersion` namespace, so they can be removed in the future 2 years ago
  Martin Evans 2830e5755c - Applied a lot of minor R# code quality suggestions. Lots of unnecessary imports removed. 2 years ago
  Martin Evans 759ae26f36
Merge branch 'master' into grammar_basics 2 years ago
  Martin Evans 4738c26299 - Reduced context size of test, to speed it up 2 years ago
  Martin Evans 64416ca23c - Created a slightly nicer way to create grammar (from `IReadOnlyList<IReadOnlyList<LLamaGrammarElement>>`) 2 years ago
  Martin Evans fda7e1c038 Fixed mirostat/mirostate 2 years ago
  Martin Evans f3511e390f WIP demonstrating changes to support multi-context. You can see this in use in `TalkToYourself`, along with notes on what still needs improving. 2 years ago
  Martin Evans 270c6d55ef
Merge pull request #88 from martindevans/fix_serialization_nan 2 years ago
  Martin Evans b5de3ee5aa Fixed some final mentions of "mirostate" instead of "mirostat" 2 years ago
  Martin Evans 0e5e00e300 Moved `TokenToString` from Utils into `SafeLLamaContextHandle` (thin wrappers around the same method in `SafeLlamaModelHandle`) 2 years ago
  Martin Evans cd3cf2b77d - Moved tokenization from `Utils.Tokenize` into `SafeLLamaContextHandle.Tokenize`, one less thing in `Utils`. 2 years ago
  sa_ddam213 bac9cba01a InferenceParams abstractions 2 years ago
  Martin Evans c64507cb41 Correctly passing through mu value to mirostate instead of resetting it every time. 2 years ago
  Yaohui Liu 6c400e64c2
docs: publiash documentation 0.4. 2 years ago
  Yaohui Liu 2eb2d6df83
test: add 9 examples of the new version. 2 years ago
  Marcel 762fd7c1ae Fixed a typo in FixedSizeQueue 2 years ago
  Yaohui Liu a3b8186f20
feat: support save and load chat session. 2 years ago
  Yaohui Liu 3bf74ec9b9
feat: add chat session for refactored code. 2 years ago
  Yaohui Liu 908b79e855
feat: add stateless executor. 2 years ago
  Yaohui Liu e603a09137
fix: state loading and saving not working. 2 years ago
  Yaohui Liu 5679e08718
feat: add ILLamaExecutor.InferAsync. 2 years ago
  Yaohui Liu 264fb9a706
refactor: LLamaModel and LLamaExecutor. 2 years ago