794b162a46
* whisper : add integer quantization support * examples : add common-ggml + prepare to add "quantize" tool * whisper : quantization tool ready * whisper : fix F32 support * whisper : try to fix shared lib linkage * wasm : update quantized models to Q5 * bench.wasm : remove "medium" button * bench.wasm : fix custom model button * ggml : add Q5_0 and Q5_1 WASM SIMD * wasm : add quantized models to all WASM examples * wasm : bump DB version number to 2 * talk-llama : update example to latest llama.cpp * node : increase test timeout to 10s * readme : add information for model quantization * wasm : add links to other examples
22 lines
580 B
C++
22 lines
580 B
C++
#pragma once
|
|
|
|
// TODO: Change to C-style API and move to ./examples for easy reuse.
|
|
|
|
#include "common.h"
|
|
|
|
#include <vector>
|
|
#include <map>
|
|
#include <string>
|
|
|
|
struct gpt2_context;
|
|
|
|
struct gpt2_context * gpt2_init(const char * path_model);
|
|
void gpt2_free(struct gpt2_context * ctx);
|
|
|
|
const char * gpt2_get_prompt(struct gpt2_context * ctx);
|
|
void gpt2_set_prompt(struct gpt2_context * ctx, const char * prompt);
|
|
|
|
std::vector<gpt_vocab::id> gpt2_tokenize(const gpt2_context * ctx, const char * text);
|
|
|
|
std::string gpt2_gen_text(gpt2_context * ctx, const char * text, int max_tokens);
|