Martin Evans
afb9d24f3a
Added model `Tokenize` method
2 years ago
Martin Evans
369c915afe
Added TokenToString conversion on model handle
2 years ago
Martin Evans
b721072aa5
Exposed some extra model properties on safe handle
2 years ago
Martin Evans
f16aa58e12
Updated to use the new loading system in llama (llama_state). This new system has split model weights and contexts into two separate things, allowing one set of weights to be shared between many contexts.
This change _only_ implements the low level API and makes no effort to update the LlamaSharp higher level abstraction.
It is built upon llama `b3f138d`, necessary DLLs are **not** included in this commit.
2 years ago
Rinne
c5e8b3eba2
Merge pull request #56 from martindevans/memory_mapped_save_loading_and_saving
Memory Mapped LoadState/SaveState
2 years ago
Rinne
1b0523f630
Merge branch 'master' into master
2 years ago
Martin Evans
4d72420a04
Replaced `SaveState` and `LoadState` implementations. These new implementations map the file into memory and then pass the pointer directly into the native API. This improves things in two ways:
- A C# array cannot exceed 2,147,483,591 bytes. In my own use of LlamaSharp I encountered this limit.
- This saves an extra copy of the entire state data into a C# `byte[]`, so it should be faster.
This does _not_ fix some other places where `GetStateData` is used. I'll look at those in a separate PR.
2 years ago
SignalRT
56a37a0d7d
Update to lates llama.cpp
Adapt the interface change in llama_backend_init
2 years ago
unknown
dba866ffcf
Update API method name
2 years ago
Yaohui Liu
1062fe1a7e
feat: upgrade the native libraries.
2 years ago
Yaohui Liu
9850417a12
feat: update quantize native params.
2 years ago
Yaohui Liu
3bf74ec9b9
feat: add chat session for refactored code.
2 years ago
Yaohui Liu
264fb9a706
refactor: LLamaModel and LLamaExecutor.
2 years ago
Yaohui Liu
3a62f087fe
fix: encoding error when using other languages.
2 years ago
Yaohui Liu
18c2ff2395
refactor: instruct mode and examples.
2 years ago
Yaohui Liu
55d5a8ae51
fix: quantization error with fp16.
2 years ago
Yaohui Liu
19979f664a
feat: support loading and saving state.
2 years ago
Yaohui Liu
4314f64b9c
feat: add check for backend package.
2 years ago
Yaohui Liu
6ffcb5306b
refactor: use official api of quantization instead.
2 years ago
Yaohui Liu
118d410d52
build: revise build informations.
2 years ago
Yaohui Liu
856d6549de
build: add linux support.
2 years ago
Yaohui Liu
02524ae4eb
build: add package informations.
2 years ago
Yaohui Liu
d6a7997e46
feat: add gpt model.
2 years ago
Yaohui Liu
5a79edeb51
feat: add the framework and basic usages.
2 years ago