mirror of
https://github.com/nomic-ai/gpt4all
synced 2024-11-04 12:00:10 +00:00
b19a3e5b2c
most of these can just shortcut out of the model loading logic llama is a bit worse to deal with because we submodule it so I have to at least parse the hparams, and then I just use the size on disk as an estimate for the mem size (which seems reasonable since we mmap() the llama files anyway)
42 lines
1.4 KiB
C++
42 lines
1.4 KiB
C++
#ifndef REPLIT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#error This file is NOT meant to be included outside of replit.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define REPLIT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
|
|
#endif
|
|
#ifndef REPLIT_H
|
|
#define REPLIT_H
|
|
|
|
#include <string>
|
|
#include <functional>
|
|
#include <vector>
|
|
#include "llmodel.h"
|
|
|
|
#define GGML_QNT_VERSION_FACTOR 1000 // do not change this
|
|
|
|
struct ReplitPrivate;
|
|
class Replit : public LLModel {
|
|
public:
|
|
Replit();
|
|
~Replit();
|
|
|
|
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:
|
|
ReplitPrivate *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 // REPLIT_H
|