ksanchez
0bbbf171ed
Refactor executors
1 year ago
ksanchez
46a9d603f4
Add method to get BOS token.
1 year ago
ksanchez
61d143d8d8
Implement context shifting in executor base
1 year ago
Rinne
6bf010d719
Merge pull request #689 from zsogitbe/master
SemanticKernel: Correcting non-standard way of working with PromptExecutionSettings
1 year ago
Zoli Somogyi
54c01d4c2c
Making old code obsolete - SemanticKernel: Correcting working with PromptExecutionSettings
1 year ago
Rinne
0c770a528e
Merge pull request #671 from kidkych/feature/interactive-sk-chatcompletion
Optimize Semantic Kernel LLamaSharpChatCompletion when running with StatefulExecutorBase models
1 year ago
Rinne
16141adcb0
Merge pull request #711 from Norne9/master
Optional IHistoryTransform added to ChatSession.InitializeSessionFromHistoryAsync
1 year ago
Rinne
7b03e735bb
Merge pull request #709 from AsakusaRinne/format_check_ci
1 year ago
Norne9
5c60e6d4ca
Merge pull request #1 from Norne9/Norne9-patch-chat-session
Optional IHistoryTransform added to ChatSession.InitializeSessionFromHistoryAsync
1 year ago
Norne9
ad9bf1cbba
InitializeSessionFromHistoryAsync changed
ChatSession.InitializeSessionFromHistoryAsync now accepts IHistoryTransform as an optional parameter.
1 year ago
Rinne
33d5677c0e
Add editorconfig file for code format.
1 year ago
Rinne
f44c8846f5
Merge pull request #710 from AsakusaRinne/typo_check_ci
ci: add workflow to check the spellings.
1 year ago
Rinne
495177fd0f
fix: typos.
1 year ago
Rinne
de31a06a4a
ci: add workflow to check the spelling.
1 year ago
Rinne
98909dc2af
Merge pull request #708 from AsakusaRinne/llama3_support
Add LLaMA3 chat session example.
1 year ago
Martin Evans
4c078a757c
Merge pull request #703 from martindevans/llava_async_load
LLava Async Loading
1 year ago
Rinne
175b25d4f7
Add LLaMA3 chat session example.
1 year ago
Martin Evans
377ebf3664
- Added `LoadFromFileAsync` method for `LLavaWeights`
- Fixed checking for invalid handles in `clip_model_load`
1 year ago
Martin Evans
84bb5a36ab
Merge pull request #702 from martindevans/interruptible_async_model_load
Interruptible Async Model Loading With Progress Monitoring
1 year ago
Martin Evans
1ec0fee5ba
Added optional `IProgress` parameter to `LoadFromFileAsync`
1 year ago
Zoli Somogyi
2aa96b206f
Adding Response Format - Correcting non-standard way of working with PromptExecutionSettings
can be used downstream to post-process the messages based on the requested format
1 year ago
Martin Evans
9867b4c85d
Only setting callback if the token can be cancelled.
1 year ago
Martin Evans
00df7c1516
- Added `LLamaWeights.LoadFromFileAsync`.
- Async loading supports cancellation through a `CancellationToken`. If loading is cancelled an `OperationCanceledException` is thrown. If it fails for another reason a `LoadWeightsFailedException` is thrown.
- Updated examples to use `LoadFromFileAsync`
1 year ago
Rinne
b47ed9258f
Merge pull request #701 from AsakusaRinne/add_issue_template
Fix typo in issue templates.
1 year ago
Rinne
bcf3ef1e40
Fix typo in issue templates.
1 year ago
Rinne
c6565c3aaf
Merge pull request #700 from AsakusaRinne/add_issue_template
Add issue templates.
1 year ago
Rinne
d56eb1a5ad
Add issue templates.
1 year ago
Martin Evans
18586cc43b
Merge pull request #696 from martindevans/safe_handle_constructor_refactor
Removed Unnecessary Constructor From Safe Handles
1 year ago
Martin Evans
e9fd7f96e0
Merge pull request #691 from martindevans/empty_batch_check
Empty batch check
1 year ago
Martin Evans
a2f8573831
Merge pull request #698 from martindevans/slightly_safer_quantize_params
Slightly Safer Quantize Params
1 year ago
Martin Evans
d4f793a7eb
Using `is` check instead of `== null`
1 year ago
Martin Evans
ecb359c9e7
- Using more specific `LoadWeightsFailedException` when a llava model fails to load ( #697 )
- Passing model path, instead of a message, to `LoadWeightsFailedException` constructor
1 year ago
Martin Evans
58ec798bff
Modified `llama_model_quantize` to accept argument by `ref` instead of pointer.
1 year ago
Martin Evans
54dab273cd
- Removed unnecessary constructors from safe handles
- Returning SafeLLamaGrammarHandle directly from `llama_grammar_init` and `llama_grammar_copy`
1 year ago
Martin Evans
25812762c9
Added checks in `Decode` to skip doing anything if the batch is empty.
1 year ago
Zoli Somogyi
59a0afdb77
Renaming files to correspond to class names
1 year ago
Zoli Somogyi
ab8dd0dfc7
Correcting non-standard way of working with PromptExecutionSettings
The extension of PromptExecutionSettings is not only for ChatCompletion, but also for text completion and text embedding.
1 year ago
Zoli Somogyi
156d7bb463
Revert "Standardizing Image Data implementation"
This reverts commit b2423fe6e9 .
1 year ago
Zoli Somogyi
6bd269da60
Revert "Simplifying image handling"
This reverts commit f264024666 .
1 year ago
Zoli Somogyi
8ea82bcc28
Revert "Embeddings correction"
This reverts commit 3ded2dd74d .
1 year ago
Zoli Somogyi
5a4c0d4637
Revert "Automatic Solution Generator - Work in progress"
This reverts commit b1f3987fae .
1 year ago
Zoli Somogyi
5a196ec6f9
Reapply "Automatic Solution Generator - Work in progress"
This reverts commit ad2c81d957 .
1 year ago
Zoli Somogyi
ad2c81d957
Revert "Automatic Solution Generator - Work in progress"
This reverts commit 9c91fac20f .
1 year ago
Zoli Somogyi
b1f3987fae
Automatic Solution Generator - Work in progress
1 year ago
Zoli Somogyi
3ded2dd74d
Embeddings correction
1 year ago
Zoli Somogyi
f264024666
Simplifying image handling
1 year ago
Zoli Somogyi
b2423fe6e9
Standardizing Image Data implementation
1 year ago
Martin Evans
ccc49eb1e0
BatchedExecutor Save/Load ( #681 )
* Added the ability to save and load individual conversations in a batched executor.
- New example
- Added `BatchedExecutor.Load(filepath)` method
- Added `Conversation.Save(filepath)` method
- Added new (currently internal) `SaveState`/`LoadState` methods in LLamaContext which can stash some extra binary data in the header
* Added ability to save/load a `Conversation` to an in-memory state, instead of to file.
* Moved the new save/load methods out to an extension class specifically for the batched executor.
* Removed unnecessary spaces
1 year ago
Chirag Karia
05937de5dc
Merge branch 'SciSharp:master' into feature/interactive-sk-chatcompletion
1 year ago
Lyrcaxis
f01c13ee54
Made special tokens included in prompts tokenize as intended ( #677 )
1 year ago