Rinne
8f3f608bfa
debug
2 years ago
Rinne
851b8fa0f6
debug
2 years ago
Rinne
ec92b64638
debug
2 years ago
Rinne
0a1f150025
debug
2 years ago
Rinne
ba7663aa1c
debug
2 years ago
Rinne
1fc35ad88b
debug
2 years ago
Rinne
2eae0cd643
debug
2 years ago
Rinne
9076d44152
debug
2 years ago
Rinne
d6097ac5d1
fix error
2 years ago
Rinne
ee55cc2981
debug
2 years ago
Rinne
2a1e15040b
Change the way to cache models.
2 years ago
Rinne
1efce65658
fix error.
2 years ago
Rinne
413c23cab9
feat: add benchmark test for prefill.
2 years ago
Rinne
c07c4ccf28
debug
2 years ago
Rinne
8e57b56b3f
debug
2 years ago
Rinne
5d76857a59
debug
2 years ago
Rinne
a573932531
debug
2 years ago
Rinne
9d3eb384f3
change cuda11 docker image
2 years ago
Rinne
5fe4814d8d
fix runner error.
2 years ago
Rinne
ff9e4f2a94
debug
2 years ago
Rinne
9423a8a7b3
ci: add benchmark test.
2 years ago
Martin Evans
05100184f4
Merge pull request #719 from martindevans/remove-batched-conversation-prompt-with-string
Remove `Conversation.Prompt(String)`
2 years ago
Martin Evans
3ba49754b1
Removed (marked as obsolete) prompting with a string for `Conversation`. Tokenization requires extra parameters (e.g. addBos, special) which require special considersation. For now it's better to tokenize using other tools and pass the tokens directly.
2 years ago
Martin Evans
9906871f84
Merge pull request #714 from ksanman/infinite-context
Implement context shifting in executor base
2 years ago
ksanchez
0bbbf171ed
Refactor executors
2 years ago
ksanchez
46a9d603f4
Add method to get BOS token.
2 years ago
ksanchez
61d143d8d8
Implement context shifting in executor base
2 years ago
Rinne
6bf010d719
Merge pull request #689 from zsogitbe/master
SemanticKernel: Correcting non-standard way of working with PromptExecutionSettings
2 years ago
Zoli Somogyi
54c01d4c2c
Making old code obsolete - SemanticKernel: Correcting working with PromptExecutionSettings
2 years ago
Rinne
0c770a528e
Merge pull request #671 from kidkych/feature/interactive-sk-chatcompletion
Optimize Semantic Kernel LLamaSharpChatCompletion when running with StatefulExecutorBase models
2 years ago
Rinne
16141adcb0
Merge pull request #711 from Norne9/master
Optional IHistoryTransform added to ChatSession.InitializeSessionFromHistoryAsync
2 years ago
Rinne
7b03e735bb
Merge pull request #709 from AsakusaRinne/format_check_ci
2 years ago
Norne9
5c60e6d4ca
Merge pull request #1 from Norne9/Norne9-patch-chat-session
Optional IHistoryTransform added to ChatSession.InitializeSessionFromHistoryAsync
2 years ago
Norne9
ad9bf1cbba
InitializeSessionFromHistoryAsync changed
ChatSession.InitializeSessionFromHistoryAsync now accepts IHistoryTransform as an optional parameter.
2 years ago
Rinne
33d5677c0e
Add editorconfig file for code format.
2 years ago
Rinne
f44c8846f5
Merge pull request #710 from AsakusaRinne/typo_check_ci
ci: add workflow to check the spellings.
2 years ago
Rinne
495177fd0f
fix: typos.
2 years ago
Rinne
de31a06a4a
ci: add workflow to check the spelling.
2 years ago
Rinne
98909dc2af
Merge pull request #708 from AsakusaRinne/llama3_support
Add LLaMA3 chat session example.
2 years ago
Martin Evans
4c078a757c
Merge pull request #703 from martindevans/llava_async_load
LLava Async Loading
2 years ago
Rinne
175b25d4f7
Add LLaMA3 chat session example.
2 years ago
Martin Evans
377ebf3664
- Added `LoadFromFileAsync` method for `LLavaWeights`
- Fixed checking for invalid handles in `clip_model_load`
2 years ago
Martin Evans
84bb5a36ab
Merge pull request #702 from martindevans/interruptible_async_model_load
Interruptible Async Model Loading With Progress Monitoring
2 years ago
Martin Evans
1ec0fee5ba
Added optional `IProgress` parameter to `LoadFromFileAsync`
2 years 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
2 years ago
Martin Evans
9867b4c85d
Only setting callback if the token can be cancelled.
2 years 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`
2 years ago
Rinne
b47ed9258f
Merge pull request #701 from AsakusaRinne/add_issue_template
Fix typo in issue templates.
2 years ago
Rinne
bcf3ef1e40
Fix typo in issue templates.
2 years ago
Rinne
c6565c3aaf
Merge pull request #700 from AsakusaRinne/add_issue_template
Add issue templates.
2 years ago