gpt4all/gpt4all-backend/gptj_impl.h
Aaron Miller 88616fde7f
llmodel: change tokenToString to not use string_view (#968)
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)
2023-06-13 07:14:02 -04:00

39 lines
1.2 KiB
C++

#ifndef GPTJ_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
#error This file is NOT meant to be included outside of gptj.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define GPTJ_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
#endif
#ifndef GPTJ_H
#define GPTJ_H
#include <string>
#include <functional>
#include <vector>
#include "llmodel.h"
struct GPTJPrivate;
class GPTJ : public LLModel {
public:
GPTJ();
~GPTJ();
bool loadModel(const std::string &modelPath) override;
bool isModelLoaded() const override;
size_t stateSize() const override;
size_t saveState(uint8_t *dest) const override;
size_t restoreState(const uint8_t *src) override;
void setThreadCount(int32_t n_threads) override;
int32_t threadCount() const override;
private:
GPTJPrivate *d_ptr;
protected:
std::vector<Token> tokenize(PromptContext &, const std::string&) const override;
Token sampleToken(PromptContext &ctx) const override;
std::string tokenToString(Token) const override;
bool evalTokens(PromptContext &ctx, const std::vector<int32_t> &tokens) const override;
int32_t contextLength() const override;
const std::vector<Token>& endTokens() const override;
};
#endif // GPTJ_H