Distribute and run LLMs with a single file.
C++ cross-platformggufllama-cpplocal-ailocal-inferencelocal-llmopen-source-aisingle-file-executablespeech-to-text
Fix sed commands in README.md
Justine Tunney2b91eff0ec7c
diff --git a/README.md b/README.mdindex 9d0e3dd6..050bf6cd 100644--- a/README.md+++ b/README.md@@ -311,7 +311,7 @@ Here's an example of how you can use llamafile to summarize HTML URLs:-force-html \-width 500 \-dump https://www.poetryfoundation.org/poems/48860/the-raven |- sed 's/ */ /'+ sed 's/ */ /g'echo '[/INST]') | llamafile \-m mistral-7b-instruct-v0.1.Q4_K_M.gguf \@@ -347,7 +347,7 @@ llamafile --temp 0 \--grammar 'root ::= [a-z]+ (" " [a-z]+)+' \-p $'### User: What do you see?\n### Assistant: ' \--silent-prompt 2>/dev/null |- sed -e's/ /_/' -e's/$/.jpg/'+ sed -e's/ /_/g' -e's/$/.jpg/'a_baby_monkey_on_the_back_of_a_mother.jpg```