mirror of
https://github.com/nomic-ai/gpt4all
synced 2024-11-04 12:00:10 +00:00
198b5e4832
Tested with https://huggingface.co/TheBloke/falcon-7b-instruct-GGML/blob/main/falcon7b-instruct.ggmlv3.q4_0.bin
41 lines
1.4 KiB
C++
41 lines
1.4 KiB
C++
#ifndef FALCON_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#error This file is NOT meant to be included outside of falcon.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define FALCON_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#endif
|
|
#ifndef FALCON_H
|
|
#define FALCON_H
|
|
|
|
#include <string>
|
|
#include <functional>
|
|
#include <vector>
|
|
#include <memory>
|
|
#include "llmodel.h"
|
|
|
|
struct FalconPrivate;
|
|
class Falcon : public LLModel {
|
|
public:
|
|
Falcon();
|
|
~Falcon();
|
|
|
|
bool loadModel(const std::string &modelPath) override;
|
|
bool isModelLoaded() const override;
|
|
size_t requiredMem(const std::string &modelPath) 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:
|
|
std::unique_ptr<FalconPrivate> 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 // Falcon_H
|