Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Add known issue for Windows
Justine Tunney29807cce0871
diff --git a/LICENSE b/LICENSEindex 7364c1eb..7661d5fd 100644--- a/LICENSE+++ b/LICENSE@@ -1,3 +1,5 @@+The Apache 2.0 License+Copyright 2023 Mozilla FoundationLicensed under the Apache License, Version 2.0 (the "License");diff --git a/README.md b/README.mdindex 433e2ae7..70e888f7 100644--- a/README.md+++ b/README.md@@ -313,3 +313,9 @@ While the llamafile project is Apache 2.0-licensed, our changesto llama.cpp are licensed under MIT (just like the llama.cpp projectitself) so as to remain compatible and upstreamable in the future,should that be desired.++## Known Issues++- Windows has a 2GB file size limit. While llamafile will work fine on+ Windows with the weights as a separate file, you'll get an error if+ you load them into the executable itself.