Martin Evans
|
4e9b1f8cdc
|
- Split extension methods into separate files
|
2 years ago |
Martin Evans
|
0f03e8f1a3
|
Added workaround to LLama.Web and LLama.WebAPI
|
2 years ago |
Martin Evans
|
669ae47ef7
|
- Split parameters into two interfaces
- params contains a list of loras, instead of just one
|
2 years ago |
Martin Evans
|
9a0a0ae9fe
|
Removed cloning support
|
2 years ago |
Martin Evans
|
0d40338692
|
Fixed out-of-context handling in stateless executor
|
2 years ago |
Martin Evans
|
b306ac23dd
|
Added `Decode` method to `SafeLLamaContextHandle`
|
2 years ago |
Martin Evans
|
9e958e896b
|
safe handle for batch
|
2 years ago |
Martin Evans
|
ce1fc51163
|
Added some more native methods
|
2 years ago |
Martin Evans
|
bca55eace0
|
Initial changes to match the llama.cpp changes
|
2 years ago |
Martin Evans
|
54b3eb0223
|
Merge pull request #179 from martindevans/extensions_tests
Extensions Method Unit Tests
|
2 years ago |
Martin Evans
|
fe54f6764f
|
- Added unit tests for extension methods
- Removed unused `AddRangeSpan` extension
|
2 years ago |
Rinne
|
4e68ee6117
|
docs: update document links in readme.
|
2 years ago |
Haiping
|
79fa74d59c
|
Merge pull request #177 from redthing1/fix/context-getstate
fix opaque GetState (fixes #176)
|
2 years ago |
redthing1
|
b78044347c
|
fix opaque GetState (fixes #176)
|
2 years ago |
Haiping
|
e1af7a96da
|
Merge pull request #175 from redthing1/feat/inferenceparams_record
make InferenceParams a record so we can use `with`
|
2 years ago |
redthing1
|
296ba607de
|
make InferenceParams a record so we can use with
|
2 years ago |
Haiping Chen
|
45426aefa9
|
Fix CodingAssistant InferAsync.
|
2 years ago |
Haiping
|
10678a83d6
|
Merge pull request #65 from martindevans/alternative_dependency_loading
CPU Feature Detection
|
2 years ago |
Haiping
|
f134c5af59
|
Merge pull request #163 from SignalRT/DefaultMetal
MacOS default build now is metal llama.cpp #2901
|
2 years ago |
Haiping
|
9f9903c711
|
Merge pull request #173 from martindevans/async_only
Remove non-async
|
2 years ago |
Haiping
|
c8bb680d66
|
Merge pull request #172 from Regenhardt/feature/coding-assistant
Coding assistent example
|
2 years ago |
Martin Evans
|
3f80190f85
|
Minimal changes required to remove non-async inference.
|
2 years ago |
Regenhardt Marlon
|
0049dcfb66
|
Coding Assistent: Improve user information and link to source paper
|
2 years ago |
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
|
b1e9d8240d
|
Merge pull request #149 from martindevans/removed_unused_inference_params
Removed unused properties of `InferenceParams` & `ModelParams`
|
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 |
SignalRT
|
d50c77434a
|
Merge branch 'Development' of https://github.com/SignalRT/LLamaSharp into Development
|
2 years ago |
SignalRT
|
c41e448d0e
|
ggml-metal.metal MUST be copied to output folder
Metal depends on this file to execute, and MacOS llama.cpp defaults is now METAL.
|
2 years ago |
jlsantiago
|
dd7e6351b1
|
Metal binaries should work in all cases (memory/metal)
|
2 years ago |
SignalRT
|
097cf38b58
|
Merge branch 'Development' of https://github.com/SignalRT/LLamaSharp into Development
|
2 years ago |
SignalRT
|
096293a026
|
MacOS Remove Metal as is the current default
See on Mac OS enable Metal by default #2901
|
2 years ago |
SignalRT
|
c7414472ba
|
Merge branch 'Development' of https://github.com/SignalRT/LLamaSharp into Development
|
2 years ago |
Martin Evans
|
400c7d4711
|
Fixed readme example code
|
2 years ago |
Martin Evans
|
b47977300a
|
Removed one more unused parameter
|
2 years ago |
Martin Evans
|
a1b0349561
|
Removed `ModelAlias` property (unused)
|
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 |