Martin Evans
|
89fef05362
|
This commit (5fe721bdbe) accidentally removed a load of stuff that it shouldn't. Fixed that.
Originally from these PRs:
- https://github.com/SciSharp/LLamaSharp/pull/263
- https://github.com/SciSharp/LLamaSharp/pull/259
|
2 years ago |
SignalRT
|
97006a214f
|
Merge remote-tracking branch 'upstream/master' into RuntimeDetection
|
2 years ago |
Martin Evans
|
31244ae691
|
Merge branch 'master' into YaRN_scaling_parameters
|
2 years ago |
SignalRT
|
5fe721bdbe
|
Revert "Merge branch 'pr/268' into RuntimeDetection"
This reverts commit 091b8d58b3502a99b3bfbec9db457c92cc736beb, reversing
changes made to 9b2ca9cf8e.
|
2 years ago |
Martin Evans
|
db1bc741b0
|
Modified `ContextSize` in parameters to be nullable. A null value means autodetect from the model.
|
2 years ago |
Martin Evans
|
04ee64a6be
|
Exposed YaRN scaling parameters in IContextParams
|
2 years ago |
Martin Evans
|
529b06b35b
|
- Fixed rope frequency/base to use the values in the model by default, instead of always overriding them by default!
|
2 years ago |
Martin Evans
|
6a4cd506bd
|
Added a safe `TensorSplitsCollection` to the params which prevents incorrectly setting the `tensor_splits` collection
|
2 years ago |
sa_ddam213
|
b4b4000342
|
Merge branch 'master' into upstream_master
# Conflicts:
# LLama.Web/Common/ModelOptions.cs
# LLama.Web/Services/ConnectionSessionService.cs
# LLama/LLamaStatelessExecutor.cs
# LLama/LLamaWeights.cs
|
2 years ago |
Martin Evans
|
2a38808bca
|
- Added threads to context params, replaced all thread args with `uint?`
- Replaced all binaries
|
2 years ago |
sa_ddam213
|
c9108f8311
|
Add service for managing Models and Model Contexts
|
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
|
bca55eace0
|
Initial changes to match the llama.cpp changes
|
2 years ago |
Martin Evans
|
2056078aef
|
Initial changes required for GGUF support
|
2 years ago |
Martin Evans
|
93f24f8a51
|
Switched to properly typed `Encoding` property
|
2 years ago |
Martin Evans
|
a9e6f21ab8
|
- Creating and destroying contexts in the stateless executor, saving memory. It now uses zero memory when not inferring!
- Passing encoding in the `IModelParams`, which reduces how often encoding needs to be passed around
|
2 years ago |
Martin Evans
|
2c933c57a1
|
Fixed ModelOptions in Web project
|
2 years ago |
sa_ddam213
|
2a04e31b7d
|
ModelParams abstraction
|
2 years ago |
sa_ddam213
|
d9fbd56f10
|
Strongly type connection status
|
2 years ago |