mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2024-09-19 23:35:41 +00:00
c4706d0c14
* porting over replit code model to gpt4all * replaced memory with kv_self struct * continuing debug * welp it built but lot of sus things * working model loading and somewhat working generate.. need to format response? * revert back to semi working version * finally got rid of weird formatting * figured out problem is with python bindings - this is good to go for testing * addressing PR feedback * output refactor * fixed prompt reponse collection * cleanup * addressing PR comments * building replit backend with new ggmlver code * chatllm replit and clean python files * cleanup * updated replit to match new llmodel api * match llmodel api and change size_t to Token * resolve PR comments * replit model commit comment
41 lines
1.3 KiB
C++
41 lines
1.3 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 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_view 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
|