abeab9f0a1
Bump dependencies
2023-09-12 12:19:57 +09:00
dced651f8b
Allow setting ChatRequestSettings Defaults and ChatSession
2023-09-11 19:21:51 +09:00
466722dcff
Merge pull request #165 from martindevans/better_instruct_antiprompt_checking
...
better_instruct_antiprompt_checking
2023-09-11 00:32:43 +01:00
d08a125020
Using the `TokensEndsWithAnyString` extensions for antiprompt checking in instruct executor. Simpler and more efficient.
2023-09-11 00:22:17 +01:00
149d076c98
Merge pull request #164 from martindevans/llama_get_kv_cache_token_count
...
llama_get_kv_cache_token_count
2023-09-11 00:22:12 +01:00
bba801f4b7
Added a property to get the KV cache size from a context
2023-09-11 00:10:08 +01:00
400c7d4711
Fixed readme example code
2023-09-09 16:19:27 +01:00
4dac142bd5
Merge pull request #160 from martindevans/GetState_fix
...
`GetState()` fix
2023-09-09 01:44:08 +01:00
b8d3fa123e
Merge pull request #159 from martindevans/removed_generate_result
...
Removed `GenerateResult`
2023-09-09 01:30:50 +01:00
832bf7dbe0
Simplified implementation of `GetState` and fixed a memory leak (`bigMemory` was never freed)
2023-09-09 01:30:35 +01:00
4f7b6ffdcc
Removed `GenerateResult` method that was only used in one place
2023-09-09 01:09:27 +01:00
e074cd3273
Merge pull request #158 from saddam213/ILogger
...
ILogger implementation
2023-09-09 00:49:38 +01:00
09d8f434f2
Extract LLamaLogLevel, Remove Logger class
2023-09-09 10:25:05 +12:00
949b0cde16
Replace ILLamaLogger for ILogger
2023-09-09 10:13:07 +12:00
70b36f8996
Add Microsoft.Extensions.Logging.Abstractions, update any required deps
2023-09-09 09:52:11 +12:00
d3b8ee988c
Beam Search ( #155 )
...
* Added the low level bindings to beam search.
2023-09-07 19:26:51 +01:00
a09aa86324
Merge pull request #153 from martindevans/fix_savestate_OpenOrCreate
...
Changed `OpenOrCreate` to `Create`
2023-09-06 23:03:24 +01:00
121b6357bf
Merge pull request #152 from martindevans/interact_antiprompt_matcing_improvement
...
Simplified `LLamaInteractExecutor` antiprompt matching
2023-09-06 22:38:30 +01:00
f366aa3abe
Changed `OpenOrCreate` to `Create` to fix #151
2023-09-06 22:35:41 +01:00
77bd090150
Simplified `LLamaInteractExecutor` antiprompt matching by using new extension method
2023-09-06 22:26:36 +01:00
6cb0342f60
Merge pull request #150 from martindevans/better_antiprompt_checking
...
Better Antiprompt Testing
2023-09-06 21:37:57 +01:00
d0e57a8c92
sealed test class
2023-09-06 20:11:31 +01:00
3f082c6f2c
Fixed naming in tests
2023-09-06 20:09:41 +01:00
614ba40948
- Added a `TokensEndsWithAnyString` extension to `IReadOnlyList<int>` which efficiently checks if a set of tokens ends with one of a set of strings.
...
- Minimal amount of characters converted
- Allocation free
- Added `TokensToSpan` to `SafeLlamaModelHandle` which converts as many tokens as possible into a character span
- Allocation free
2023-09-06 19:44:19 +01:00
23a7699f96
Update README.md
2023-09-05 23:39:01 -05:00
Yaohui Liu
4a0c60fe70
docs: update the readme.
2023-09-06 02:56:18 +08:00
Yaohui Liu
3067e01a4b
build: add package info for LLamaSharp.semantic-kernel
2023-09-06 02:50:23 +08:00
Rinne
f3e23d692c
Merge pull request #139 from drasticactions/embeddings-semantickernel
...
Add TextEmbedding for Semantic Kernel
2023-09-06 02:11:29 +08:00
ab633089e9
Merge branch 'master' into embeddings-semantickernel
2023-09-05 13:53:24 +09:00
037472cc3c
Merge pull request #147 from martindevans/llama2-7b-chat.gguf
...
Swapped to llama-7b-chat
2023-09-04 21:45:34 +01:00
821d7f615e
Swapped to llama-7b-chat
2023-09-04 21:26:02 +01:00
4414e7f13f
Merge pull request #146 from martindevans/duplicate_llama_sample_classifier_free_guidance
...
Removed duplicate `llama_sample_classifier_free_guidance` method
2023-09-04 01:01:49 +01:00
6a842014ac
Removed duplicate `llama_sample_classifier_free_guidance` method
2023-09-04 00:48:27 +01:00
74c19b10af
Merge pull request #145 from martindevans/disable_test_parallel
...
Disable test parallelism
2023-09-03 23:59:54 +01:00
4a53cdc56b
Merge pull request #142 from SciSharp/rinne-dev
...
refactor: remove old version files.
2023-09-03 23:36:28 +01:00
21cbecb82d
Disable test parallelism to prevent fix CI
2023-09-03 23:35:53 +01:00
b70c07963d
Merge pull request #144 from martindevans/remove_LLamaNewlineTokens
...
Remove LLamaNewlineTokens from InteractiveExecutorState
2023-09-03 20:32:57 +01:00
33035c82bf
- Removed `LLamaNewlineTokens` from `InteractiveExecutorState`. This is always set in the constructor from the context, so there's no point serializing it.
2023-09-03 18:22:39 +01:00
5a119c4ee1
Update MacOS Binaries ( #143 )
...
* Restore macOS pipelines
* Generate Metal binaries.
2023-09-03 15:15:40 +01:00
6327a04342
Merge branch 'master' into embeddings-semantickernel
2023-09-03 23:02:17 +09:00
Yaohui Liu
18294a725e
refactor: remove old version files.
2023-09-02 22:24:07 +08:00
b1f33fa20e
Placed the `noavx` file for Linux and Windows in the root `deps` folder, these will be used as the default if nothing else is loaded
2023-09-02 14:22:38 +01:00
cfb3defeee
Changed paths to no longer include OS name (no need, .dll and .so file extensions are enough)
2023-09-02 14:17:35 +01:00
025741a73e
Fixed My Name
...
The D is for my middle name 😄
2023-09-02 13:45:06 +01:00
Rinne
b82e9f8fb0
Merge pull request #141 from SciSharp/rinne-dev
...
docs: update the docs to follow new version.
2023-09-02 17:57:23 +08:00
94a395240a
Bump example, readme
2023-09-02 14:21:02 +09:00
Yaohui Liu
20b5363601
fix: remove the history commit of embedding length property.
2023-09-02 12:56:02 +08:00
bea1ca9f8d
Update
2023-09-02 13:54:38 +09:00
Yaohui Liu
3a847623ab
docs: update the docs to follow new version.
2023-09-02 12:51:51 +08:00
35266d8112
Remove MemorySkill sample
2023-09-02 13:41:59 +09:00
Tim Miller
Yaohui Liu