mirror of
https://github.com/nomic-ai/gpt4all
synced 2024-11-04 12:00:10 +00:00
88616fde7f
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)
39 lines
1.2 KiB
C++
39 lines
1.2 KiB
C++
#ifndef MPT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#error This file is NOT meant to be included outside of mpt.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define MPT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#endif
|
|
#ifndef MPT_H
|
|
#define MPT_H
|
|
|
|
#include <string>
|
|
#include <functional>
|
|
#include <vector>
|
|
#include "llmodel.h"
|
|
|
|
struct MPTPrivate;
|
|
class MPT : public LLModel {
|
|
public:
|
|
MPT();
|
|
~MPT();
|
|
|
|
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:
|
|
MPTPrivate *d_ptr;
|
|
|
|
protected:
|
|
std::vector<Token> tokenize(PromptContext &, const std::string&) const override;
|
|
std::string tokenToString(Token) const override;
|
|
Token sampleToken(PromptContext &ctx) 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 // MPT_H
|