We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f5a77a6 commit 56817b1Copy full SHA for 56817b1
README.md
@@ -5,17 +5,9 @@
5
6
Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
7
8
----
9
-
10
-**TEMPORARY NOTICE:**
11
-Big code change incoming: https://github.com/ggerganov/llama.cpp/pull/370
12
13
-Do not merge stuff until we merge this. Probably merge will happen on March 22 ~6:00am UTC
14
15
16
17
**Hot topics:**
18
+- New C-style API is now available: https://github.com/ggerganov/llama.cpp/pull/370
19
- [Added Alpaca support](https://github.com/ggerganov/llama.cpp#instruction-mode-with-alpaca)
20
- Cache input prompts for faster initialization: https://github.com/ggerganov/llama.cpp/issues/64
21
- Create a `llama.cpp` logo: https://github.com/ggerganov/llama.cpp/issues/105
0 commit comments