Regenhardt Marlon
71f4e2ae4a
Coding Assistent: Use GGUF model
2 years ago
Marlon Regenhardt
2386be58c4
Example: Add code assistant using Code Llama-7b-Instruct as default
2 years ago
Martin Evans
6a04f05e06
Merge pull request #169 from drasticactions/sk-api-update
SemanticKernel API Update
2 years ago
Tim Miller
458679e36f
Merge branch 'sk-api-update' of github.com:drasticactions/LLamaSharp into sk-api-update
2 years ago
Tim Miller
1b35da7e20
Merge branch 'master' into sk-api-update
2 years ago
Tim Miller
abeab9f0a1
Bump dependencies
2 years ago
Martin Evans
84c077067e
Merge pull request #167 from martindevans/skip_empty_tokenisation
skip_empty_tokenization
2 years ago
Martin Evans
daf09eae64
Skipping tokenization of empty strings (saves allocating an empty array every time)
2 years ago
Tim Miller
dced651f8b
Allow setting ChatRequestSettings Defaults and ChatSession
2 years ago
Martin Evans
466722dcff
Merge pull request #165 from martindevans/better_instruct_antiprompt_checking
better_instruct_antiprompt_checking
2 years ago
Martin Evans
d08a125020
Using the `TokensEndsWithAnyString` extensions for antiprompt checking in instruct executor. Simpler and more efficient.
2 years ago
Martin Evans
149d076c98
Merge pull request #164 from martindevans/llama_get_kv_cache_token_count
llama_get_kv_cache_token_count
2 years ago
Martin Evans
bba801f4b7
Added a property to get the KV cache size from a context
2 years ago
Martin Evans
400c7d4711
Fixed readme example code
2 years ago
Martin Evans
4dac142bd5
Merge pull request #160 from martindevans/GetState_fix
`GetState()` fix
2 years ago
Martin Evans
b8d3fa123e
Merge pull request #159 from martindevans/removed_generate_result
Removed `GenerateResult`
2 years ago
Martin Evans
832bf7dbe0
Simplified implementation of `GetState` and fixed a memory leak (`bigMemory` was never freed)
2 years ago
Martin Evans
4f7b6ffdcc
Removed `GenerateResult` method that was only used in one place
2 years ago
Martin Evans
e074cd3273
Merge pull request #158 from saddam213/ILogger
ILogger implementation
2 years ago
sa_ddam213
09d8f434f2
Extract LLamaLogLevel, Remove Logger class
2 years ago
sa_ddam213
949b0cde16
Replace ILLamaLogger for ILogger
2 years ago
sa_ddam213
70b36f8996
Add Microsoft.Extensions.Logging.Abstractions, update any required deps
2 years ago
Martin Evans
d3b8ee988c
Beam Search ( #155 )
* Added the low level bindings to beam search.
2 years ago
Martin Evans
a09aa86324
Merge pull request #153 from martindevans/fix_savestate_OpenOrCreate
Changed `OpenOrCreate` to `Create`
2 years ago
Martin Evans
121b6357bf
Merge pull request #152 from martindevans/interact_antiprompt_matcing_improvement
Simplified `LLamaInteractExecutor` antiprompt matching
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
6cb0342f60
Merge pull request #150 from martindevans/better_antiprompt_checking
Better Antiprompt Testing
2 years ago
Martin Evans
d0e57a8c92
sealed test class
2 years ago
Martin Evans
3f082c6f2c
Fixed naming in tests
2 years ago
Martin Evans
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
2 years ago
Haiping
23a7699f96
Update README.md
2 years ago
Yaohui Liu
4a0c60fe70
docs: update the readme.
2 years ago
Yaohui Liu
3067e01a4b
build: add package info for LLamaSharp.semantic-kernel
2 years ago
Rinne
f3e23d692c
Merge pull request #139 from drasticactions/embeddings-semantickernel
Add TextEmbedding for Semantic Kernel
2 years ago
Tim Miller
ab633089e9
Merge branch 'master' into embeddings-semantickernel
2 years ago
Martin Evans
037472cc3c
Merge pull request #147 from martindevans/llama2-7b-chat.gguf
Swapped to llama-7b-chat
2 years ago
Martin Evans
821d7f615e
Swapped to llama-7b-chat
2 years ago
Martin Evans
4414e7f13f
Merge pull request #146 from martindevans/duplicate_llama_sample_classifier_free_guidance
Removed duplicate `llama_sample_classifier_free_guidance` method
2 years ago
Martin Evans
6a842014ac
Removed duplicate `llama_sample_classifier_free_guidance` method
2 years ago
Martin Evans
74c19b10af
Merge pull request #145 from martindevans/disable_test_parallel
Disable test parallelism
2 years ago
Martin Evans
4a53cdc56b
Merge pull request #142 from SciSharp/rinne-dev
refactor: remove old version files.
2 years ago
Martin Evans
21cbecb82d
Disable test parallelism to prevent fix CI
2 years ago
Martin Evans
b70c07963d
Merge pull request #144 from martindevans/remove_LLamaNewlineTokens
Remove LLamaNewlineTokens from InteractiveExecutorState
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
jlsantiago
5a119c4ee1
Update MacOS Binaries ( #143 )
* Restore macOS pipelines
* Generate Metal binaries.
2 years ago
Tim Miller
6327a04342
Merge branch 'master' into embeddings-semantickernel
2 years ago
Yaohui Liu
18294a725e
refactor: remove old version files.
2 years ago
Martin Evans
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
2 years ago
Martin Evans
cfb3defeee
Changed paths to no longer include OS name (no need, .dll and .so file extensions are enough)
2 years ago