gpt4all/gpt4all-backend/gptj_impl.h

39 lines
1.2 KiB
C
Raw Normal View History

#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
2023-04-08 23:28:39 -04:00
#ifndef GPTJ_H
#define GPTJ_H
#include <string>
#include <functional>
2023-04-10 15:04:40 -04:00
#include <vector>
#include "llmodel.h"
2023-04-08 23:28:39 -04:00
struct GPTJPrivate;
class GPTJ : public LLModel {
2023-04-08 23:28:39 -04:00
public:
GPTJ();
~GPTJ();
bool loadModel(const std::string &modelPath) override;
bool isModelLoaded() const override;
2023-05-05 10:00:05 -04:00
size_t stateSize() const override;
size_t saveState(uint8_t *dest) const override;
size_t restoreState(const uint8_t *src) override;
2023-04-18 09:46:03 -04:00
void setThreadCount(int32_t n_threads) override;
int32_t threadCount() const override;
2023-04-08 23:28:39 -04:00
private:
GPTJPrivate *d_ptr;
protected:
std::vector<Token> tokenize(PromptContext &, const std::string&) const override;
Token sampleToken(PromptContext &ctx) const override;
std::string_view 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;
2023-04-08 23:28:39 -04:00
};
2023-04-18 09:46:03 -04:00
#endif // GPTJ_H