github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-07 11:30:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

llmodel: change tokenToString to not use string_view (#968)

Browse Source 
fixes a definite use-after-free and likely avoids some other
potential ones - std::string will convert to a std::string_view
automatically but as soon as the std::string in question goes out of
scope it is already freed and the string_view is pointing at freed
memory - this is *mostly* fine if its returning a reference to the
tokenizer's internal vocab table but it's, imo, too easy to return a
reference to a dynamically constructed string with this as replit is
doing (and unfortunately needs to do to convert the internal whitespace
replacement symbol back to a space)
This commit is contained in:
Aaron Miller
2023-06-13 04:14:02 -07:00
committed by GitHub
parent 726dcbd43d
commit 88616fde7f
11 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
gpt4all-backend/llmodel.h
View File

@@ -86,7 +86,7 @@ protected:
// These are pure virtual because subclasses need to implement as the default implementation of
// 'prompt' above calls these functions
virtual std::vector<Token> tokenize(PromptContext &, const std::string&) const = 0;
virtual std::string_view tokenToString(Token) const = 0;
virtual std::string tokenToString(Token) const = 0;
virtual Token sampleToken(PromptContext &ctx) const = 0;
virtual bool evalTokens(PromptContext &/*ctx*/, const std::vector<int32_t>& /*tokens*/) const = 0;
virtual int32_t contextLength() const = 0;