forked from nomic-ai/gpt4all
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bert_impl.h
44 lines (37 loc) · 1.52 KB
/
bert_impl.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
#ifndef BERT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
#error This file is NOT meant to be included outside of bert.cpp. Doing so is DANGEROUS. Be sure to know what you are doing before proceeding to #define BERT_H_I_KNOW_WHAT_I_AM_DOING_WHEN_INCLUDING_THIS_FILE
#endif
#ifndef BERT_H
#define BERT_H
#include <string>
#include <functional>
#include <vector>
#include <memory>
#include "llmodel.h"
struct BertPrivate;
class Bert : public LLModel {
public:
Bert();
~Bert();
bool supportsEmbedding() const override { return true; }
bool supportsCompletion() const override { return true; }
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;
std::vector<float> embedding(const std::string &text) override;
private:
std::unique_ptr<BertPrivate> 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 // BERT_H