You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+2-14Lines changed: 2 additions & 14 deletions
Original file line number
Diff line number
Diff line change
@@ -11,21 +11,9 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
11
11
12
12
### Hot topics
13
13
14
-
-#### IMPORTANT: Tokenizer fixes and API change (developers and projects using `llama.cpp` built-in tokenization must read): https://github.com/ggerganov/llama.cpp/pull/2810
14
+
-Local Falcon 180B inference on Mac Studio
15
15
16
-
- GGUFv2 adds support for 64-bit sizes + backwards compatible: https://github.com/ggerganov/llama.cpp/pull/2821
17
-
18
-
- Added support for Falcon models: https://github.com/ggerganov/llama.cpp/pull/2717
19
-
20
-
- A new file format has been introduced: [GGUF](https://github.com/ggerganov/llama.cpp/pull/2398)
21
-
22
-
Last revision compatible with the old format: [dadbed9](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa)
23
-
24
-
### Current `master` should be considered in Beta - expect some issues for a few days!
25
-
26
-
### Be prepared to re-convert and / or re-quantize your GGUF models while this notice is up!
27
-
28
-
### Issues with non-GGUF models will be considered with low priority!
0 commit comments