mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 19:34:35 +00:00
7eee341bee
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-musa.Dockerfile platforms:linux/amd64 tag:full-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-musa.Dockerfile platforms:linux/amd64 tag:light-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-musa.Dockerfile platforms:linux/amd64 tag:server-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
* common : use common_ prefix for common library functions --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
46 lines
1.2 KiB
C++
46 lines
1.2 KiB
C++
#include "arg.h"
|
|
#include "common.h"
|
|
#include "ngram-cache.h"
|
|
#include "ggml.h"
|
|
#include "llama.h"
|
|
|
|
#include <cstdint>
|
|
#include <fstream>
|
|
#include <iostream>
|
|
#include <string>
|
|
#include <unordered_map>
|
|
#include <vector>
|
|
|
|
int main(int argc, char ** argv){
|
|
common_params params;
|
|
|
|
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_LOOKUP)) {
|
|
return 1;
|
|
}
|
|
|
|
// init llama.cpp
|
|
llama_backend_init();
|
|
llama_numa_init(params.numa);
|
|
|
|
// load the model
|
|
common_init_result llama_init = common_init_from_params(params);
|
|
|
|
llama_model * model = llama_init.model;
|
|
llama_context * ctx = llama_init.context;
|
|
GGML_ASSERT(model != nullptr);
|
|
|
|
// tokenize the prompt
|
|
std::vector<llama_token> inp;
|
|
inp = common_tokenize(ctx, params.prompt, true, true);
|
|
fprintf(stderr, "%s: tokenization done\n", __func__);
|
|
|
|
|
|
common_ngram_cache ngram_cache;
|
|
common_ngram_cache_update(ngram_cache, LLAMA_NGRAM_STATIC, LLAMA_NGRAM_STATIC, inp, inp.size(), true);
|
|
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.lookup_cache_static.c_str());
|
|
|
|
common_ngram_cache_save(ngram_cache, params.lookup_cache_static);
|
|
|
|
return 0;
|
|
}
|