diff options
Diffstat (limited to 'common/common.cpp')
| -rw-r--r-- | common/common.cpp | 323 |
1 files changed, 314 insertions, 9 deletions
diff --git a/common/common.cpp b/common/common.cpp index 0d91a6a3..4a0d43c1 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1,15 +1,20 @@ #include "common.h" +#include "build-info.h" +#include "llama.h" +#include <algorithm> #include <cassert> -#include <iostream> +#include <cmath> #include <cstring> +#include <ctime> #include <fstream> -#include <string> #include <iterator> -#include <algorithm> +#include <iostream> +#include <regex> #include <sstream> +#include <string> #include <unordered_set> -#include <regex> +#include <vector> #if defined(__APPLE__) && defined(__MACH__) #include <sys/types.h> @@ -19,11 +24,14 @@ #if defined(_WIN32) #define WIN32_LEAN_AND_MEAN #define NOMINMAX +#include <codecvt> +#include <locale> #include <windows.h> #include <fcntl.h> #include <io.h> #else #include <sys/ioctl.h> +#include <sys/stat.h> #include <unistd.h> #endif @@ -93,7 +101,6 @@ void process_escapes(std::string& input) { bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { bool invalid_param = false; - bool escape_prompt = false; std::string arg; gpt_params default_params; const std::string arg_prefix = "--"; @@ -125,8 +132,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { break; } params.prompt = argv[i]; - } else if (arg == "-e") { - escape_prompt = true; + } else if (arg == "-e" || arg == "--escape") { + params.escape = true; } else if (arg == "--prompt-cache") { if (++i >= argc) { invalid_param = true; @@ -415,6 +422,16 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { break; } params.antiprompt.push_back(argv[i]); + } else if (arg == "-ld" || arg == "--logdir") { + if (++i >= argc) { + invalid_param = true; + break; + } + params.logdir = argv[i]; + + if (params.logdir.back() != DIRECTORY_SEPARATOR) { + params.logdir += DIRECTORY_SEPARATOR; + } } else if (arg == "--perplexity") { params.perplexity = true; } else if (arg == "--ppl-stride") { @@ -520,7 +537,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { exit(1); } - if (escape_prompt) { + if (params.escape) { process_escapes(params.prompt); process_escapes(params.input_prefix); process_escapes(params.input_suffix); @@ -546,7 +563,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); fprintf(stdout, " -p PROMPT, --prompt PROMPT\n"); fprintf(stdout, " prompt to start generation with (default: empty)\n"); - fprintf(stdout, " -e process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n"); + fprintf(stdout, " -e, --escape process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n"); fprintf(stdout, " --prompt-cache FNAME file to cache prompt state for faster startup (default: none)\n"); fprintf(stdout, " --prompt-cache-all if specified, saves user input and generations to cache as well.\n"); fprintf(stdout, " not supported with --interactive or other interactive options\n"); @@ -627,6 +644,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { fprintf(stdout, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n"); fprintf(stdout, " -m FNAME, --model FNAME\n"); fprintf(stdout, " model path (default: %s)\n", params.model.c_str()); + fprintf(stdout, " -ld LOGDIR, --logdir LOGDIR\n"); + fprintf(stdout, " path under which to save YAML logs (no logging if unset)\n"); fprintf(stdout, "\n"); } @@ -779,3 +798,289 @@ std::string llama_detokenize_bpe(llama_context * ctx, const std::vector<llama_to return result; } + +// returns true if successful, false otherwise +bool create_directory_with_parents(const std::string & path) { +#ifdef _WIN32 + std::wstring_convert<std::codecvt_utf8<wchar_t>> converter; + std::wstring wpath = converter.from_bytes(path); + + // if the path already exists, check whether it's a directory + const DWORD attributes = GetFileAttributesW(wpath.c_str()); + if ((attributes != INVALID_FILE_ATTRIBUTES) && (attributes & FILE_ATTRIBUTE_DIRECTORY)) { + return true; + } + + size_t pos_slash = 0; + + // process path from front to back, procedurally creating directories + while ((pos_slash = path.find('\\', pos_slash)) != std::string::npos) { + const std::wstring subpath = wpath.substr(0, pos_slash); + const wchar_t * test = subpath.c_str(); + + const bool success = CreateDirectoryW(test, NULL); + if (!success) { + const DWORD error = GetLastError(); + + // if the path already exists, ensure that it's a directory + if (error == ERROR_ALREADY_EXISTS) { + const DWORD attributes = GetFileAttributesW(subpath.c_str()); + if (attributes == INVALID_FILE_ATTRIBUTES || !(attributes & FILE_ATTRIBUTE_DIRECTORY)) { + return false; + } + } else { + return false; + } + } + + pos_slash += 1; + } + + return true; +#else + // if the path already exists, check whether it's a directory + struct stat info; + if (stat(path.c_str(), &info) == 0) { + return S_ISDIR(info.st_mode); + } + + size_t pos_slash = 1; // skip leading slashes for directory creation + + // process path from front to back, procedurally creating directories + while ((pos_slash = path.find('/', pos_slash)) != std::string::npos) { + const std::string subpath = path.substr(0, pos_slash); + struct stat info; + + // if the path already exists, ensure that it's a directory + if (stat(subpath.c_str(), &info) == 0) { + if (!S_ISDIR(info.st_mode)) { + return false; + } + } else { + // create parent directories + const int ret = mkdir(subpath.c_str(), 0755); + if (ret != 0) { + return false; + } + } + + pos_slash += 1; + } + + return true; +#endif // _WIN32 +} + +void dump_vector_float_yaml(FILE * stream, const char * prop_name, const std::vector<float> & data) { + if (data.empty()) { + fprintf(stream, "%s:\n", prop_name); + return; + } + + fprintf(stream, "%s: [", prop_name); + for (size_t i = 0; i < data.size() - 1; ++i) { + fprintf(stream, "%e, ", data[i]); + } + fprintf(stream, "%e]\n", data.back()); +} + +void dump_vector_int_yaml(FILE * stream, const char * prop_name, const std::vector<int> & data) { + if (data.empty()) { + fprintf(stream, "%s:\n", prop_name); + return; + } + + fprintf(stream, "%s: [", prop_name); + for (size_t i = 0; i < data.size() - 1; ++i) { + fprintf(stream, "%d, ", data[i]); + } + fprintf(stream, "%d]\n", data.back()); +} + +void dump_string_yaml_multiline(FILE * stream, const char * prop_name, const char * data) { + std::string data_str(data == NULL ? "" : data); + + if (data_str.empty()) { + fprintf(stream, "%s:\n", prop_name); + return; + } + + size_t pos_start = 0; + size_t pos_found = 0; + + if (!data_str.empty() && (std::isspace(data_str[0]) || std::isspace(data_str.back()))) { + data_str = std::regex_replace(data_str, std::regex("\n"), "\\n"); + data_str = std::regex_replace(data_str, std::regex("\""), "\\\""); + data_str = "\"" + data_str + "\""; + fprintf(stream, "%s: %s\n", prop_name, data_str.c_str()); + return; + } + + if (data_str.find('\n') == std::string::npos) { + fprintf(stream, "%s: %s\n", prop_name, data_str.c_str()); + return; + } + + fprintf(stream, "%s: |\n", prop_name); + while ((pos_found = data_str.find('\n', pos_start)) != std::string::npos) { + fprintf(stream, " %s\n", data_str.substr(pos_start, pos_found-pos_start).c_str()); + pos_start = pos_found + 1; + } +} + +std::string get_sortable_timestamp() { + using clock = std::chrono::system_clock; + + const clock::time_point current_time = clock::now(); + const time_t as_time_t = clock::to_time_t(current_time); + char timestamp_no_ns[100]; + std::strftime(timestamp_no_ns, 100, "%Y_%m_%d-%H_%M_%S", std::localtime(&as_time_t)); + + const int64_t ns = std::chrono::duration_cast<std::chrono::nanoseconds>( + current_time.time_since_epoch() % 1000000000).count(); + char timestamp_ns[10]; + snprintf(timestamp_ns, 11, "%09ld", ns); + + return std::string(timestamp_no_ns) + "." + std::string(timestamp_ns); +} + +void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const llama_context * lctx, + const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc) { + fprintf(stream, "build_commit: %s\n", BUILD_COMMIT); + fprintf(stream, "build_number: %d\n", BUILD_NUMBER); + fprintf(stream, "cpu_has_arm_fma: %s\n", ggml_cpu_has_arm_fma() ? "true" : "false"); + fprintf(stream, "cpu_has_avx: %s\n", ggml_cpu_has_avx() ? "true" : "false"); + fprintf(stream, "cpu_has_avx2: %s\n", ggml_cpu_has_avx2() ? "true" : "false"); + fprintf(stream, "cpu_has_avx512: %s\n", ggml_cpu_has_avx512() ? "true" : "false"); + fprintf(stream, "cpu_has_avx512_vbmi: %s\n", ggml_cpu_has_avx512_vbmi() ? "true" : "false"); + fprintf(stream, "cpu_has_avx512_vnni: %s\n", ggml_cpu_has_avx512_vnni() ? "true" : "false"); + fprintf(stream, "cpu_has_blas: %s\n", ggml_cpu_has_blas() ? "true" : "false"); + fprintf(stream, "cpu_has_cublas: %s\n", ggml_cpu_has_cublas() ? "true" : "false"); + fprintf(stream, "cpu_has_clblast: %s\n", ggml_cpu_has_clblast() ? "true" : "false"); + fprintf(stream, "cpu_has_fma: %s\n", ggml_cpu_has_fma() ? "true" : "false"); + fprintf(stream, "cpu_has_gpublas: %s\n", ggml_cpu_has_gpublas() ? "true" : "false"); + fprintf(stream, "cpu_has_neon: %s\n", ggml_cpu_has_neon() ? "true" : "false"); + fprintf(stream, "cpu_has_f16c: %s\n", ggml_cpu_has_f16c() ? "true" : "false"); + fprintf(stream, "cpu_has_fp16_va: %s\n", ggml_cpu_has_fp16_va() ? "true" : "false"); + fprintf(stream, "cpu_has_wasm_simd: %s\n", ggml_cpu_has_wasm_simd() ? "true" : "false"); + fprintf(stream, "cpu_has_blas: %s\n", ggml_cpu_has_blas() ? "true" : "false"); + fprintf(stream, "cpu_has_sse3: %s\n", ggml_cpu_has_sse3() ? "true" : "false"); + fprintf(stream, "cpu_has_vsx: %s\n", ggml_cpu_has_vsx() ? "true" : "false"); + +#ifdef NDEBUG + fprintf(stream, "debug: false\n"); +#else + fprintf(stream, "debug: true\n"); +#endif // NDEBUG + + fprintf(stream, "model_desc: %s\n", model_desc); + fprintf(stream, "n_vocab: %d # output size of the final layer, 32001 for some models\n", llama_n_vocab(lctx)); + +#ifdef __OPTIMIZE__ + fprintf(stream, "optimize: true\n"); +#else + fprintf(stream, "optimize: false\n"); +#endif // __OPTIMIZE__ + + fprintf(stream, "time: %s\n", timestamp.c_str()); + + fprintf(stream, "\n"); + fprintf(stream, "###############\n"); + fprintf(stream, "# User Inputs #\n"); + fprintf(stream, "###############\n"); + fprintf(stream, "\n"); + + fprintf(stream, "alias: %s # default: unknown\n", params.model_alias.c_str()); + fprintf(stream, "batch_size: %d # default: 512\n", params.n_batch); + dump_string_yaml_multiline(stream, "cfg_negative_prompt", params.cfg_negative_prompt.c_str()); + fprintf(stream, "cfg_scale: %f # default: 1.0\n", params.cfg_scale); + fprintf(stream, "chunks: %d # default: -1 (unlimited)\n", params.n_chunks); + fprintf(stream, "color: %s # default: false\n", params.use_color ? "true" : "false"); + fprintf(stream, "ctx_size: %d # default: 512\n", params.n_ctx); + fprintf(stream, "escape: %s # default: false\n", params.escape ? "true" : "false"); + fprintf(stream, "export: %s # default: false\n", params.export_cgraph ? "true" : "false"); + fprintf(stream, "file: # never logged, see prompt instead. Can still be specified for input.\n"); + fprintf(stream, "frequency_penalty: %f # default: 0.0 \n", params.frequency_penalty); + dump_string_yaml_multiline(stream, "grammar", params.grammar.c_str()); + fprintf(stream, "grammar-file: # never logged, see grammar instead. Can still be specified for input.\n"); + fprintf(stream, "hellaswag: %s # default: false\n", params.hellaswag ? "true" : "false"); + fprintf(stream, "hellaswag_tasks: %ld # default: 400\n", params.hellaswag_tasks); + + const auto logit_bias_eos = params.logit_bias.find(llama_token_eos(lctx)); + const bool ignore_eos = logit_bias_eos != params.logit_bias.end() && logit_bias_eos->second == -INFINITY; + fprintf(stream, "ignore_eos: %s # default: false\n", ignore_eos ? "true" : "false"); + + dump_string_yaml_multiline(stream, "in_prefix", params.input_prefix.c_str()); + fprintf(stream, "in_prefix_bos: %s # default: false\n", params.input_prefix_bos ? "true" : "false"); + dump_string_yaml_multiline(stream, "in_suffix", params.input_prefix.c_str()); + fprintf(stream, "instruct: %s # default: false\n", params.instruct ? "true" : "false"); + fprintf(stream, "interactive: %s # default: false\n", params.interactive ? "true" : "false"); + fprintf(stream, "interactive_first: %s # default: false\n", params.interactive_first ? "true" : "false"); + fprintf(stream, "keep: %d # default: 0\n", params.n_keep); + fprintf(stream, "logdir: %s # default: unset (no logging)\n", params.logdir.c_str()); + + fprintf(stream, "logit_bias:\n"); + for (std::pair<llama_token, float> lb : params.logit_bias) { + if (ignore_eos && lb.first == logit_bias_eos->first) { + continue; + } + fprintf(stream, " %d: %f", lb.first, lb.second); + } + + fprintf(stream, "lora: %s\n", params.lora_adapter.c_str()); + fprintf(stream, "lora_base: %s\n", params.lora_base.c_str()); + fprintf(stream, "low_vram: %s # default: false\n", params.low_vram ? "true" : "false"); + fprintf(stream, "main_gpu: %d # default: 0\n", params.main_gpu); + fprintf(stream, "memory_f32: %s # default: false\n", !params.memory_f16 ? "true" : "false"); + fprintf(stream, "mirostat: %d # default: 0 (disabled)\n", params.mirostat); + fprintf(stream, "mirostat_ent: %f # default: 5.0\n", params.mirostat_tau); + fprintf(stream, "mirostat_lr: %f # default: 0.1\n", params.mirostat_eta); + fprintf(stream, "mlock: %s # default: false\n", params.use_mlock ? "true" : "false"); + fprintf(stream, "model: %s # default: models/7B/ggml-model.bin\n", params.model.c_str()); + fprintf(stream, "mtest: %s # default: false\n", params.mem_test ? "true" : "false"); + fprintf(stream, "multiline_input: %s # default: false\n", params.multiline_input ? "true" : "false"); + fprintf(stream, "n_gpu_layers: %d # default: 0\n", params.n_gpu_layers); + fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict); + fprintf(stream, "n_probs: %d # only used by server binary, default: 0\n", params.n_probs); + fprintf(stream, "no_mmap: %s # default: false\n", !params.use_mmap ? "true" : "false"); + fprintf(stream, "no_mul_mat_q: %s # default: false\n", !params.mul_mat_q ? "true" : "false"); + fprintf(stream, "no_penalize_nl: %s # default: false\n", !params.penalize_nl ? "true" : "false"); + fprintf(stream, "numa: %s # default: false\n", params.numa ? "true" : "false"); + fprintf(stream, "ppl_output_type: %d # default: 0\n", params.ppl_output_type); + fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride); + fprintf(stream, "presence_penalty: %f # default: 0.0\n", params.presence_penalty); + dump_string_yaml_multiline(stream, "prompt", params.prompt.c_str()); + fprintf(stream, "prompt_cache: %s\n", params.path_prompt_cache.c_str()); + fprintf(stream, "prompt_cache_all: %s # default: false\n", params.prompt_cache_all ? "true" : "false"); + fprintf(stream, "prompt_cache_ro: %s # default: false\n", params.prompt_cache_ro ? "true" : "false"); + dump_vector_int_yaml(stream, "prompt_tokens", prompt_tokens); + fprintf(stream, "random_prompt: %s # default: false\n", params.random_prompt ? "true" : "false"); + fprintf(stream, "repeat_penalty: %f # default: 1.1\n", params.repeat_penalty); + + fprintf(stream, "reverse_prompt:\n"); + for (std::string ap : params.antiprompt) { + size_t pos = 0; + while ((pos = ap.find('\n', pos)) != std::string::npos) { + ap.replace(pos, 1, "\\n"); + pos += 1; + } + + fprintf(stream, " - %s\n", ap.c_str()); + } + + fprintf(stream, "rope_freq_base: %f # default: 10000.0\n", params.rope_freq_base); + fprintf(stream, "rope_freq_scale: %f # default: 1.0\n", params.rope_freq_scale); + fprintf(stream, "seed: %d # default: -1 (random seed)\n", params.seed); + fprintf(stream, "simple_io: %s # default: false\n", params.simple_io ? "true" : "false"); + fprintf(stream, "temp: %f # default: 0.8\n", params.temp); + + const std::vector<float> tensor_split_vector(params.tensor_split, params.tensor_split + LLAMA_MAX_DEVICES); + dump_vector_float_yaml(stream, "tensor_split", tensor_split_vector); + + fprintf(stream, "tfs: %f # default: 1.0\n", params.tfs_z); + fprintf(stream, "threads: %d # default: %d\n", params.n_threads, std::thread::hardware_concurrency()); + fprintf(stream, "top_k: %d # default: 40\n", params.top_k); + fprintf(stream, "top_p: %f # default: 0.95\n", params.top_p); + fprintf(stream, "typical_p: %f # default: 1.0\n", params.typical_p); + fprintf(stream, "verbose_prompt: %s # default: false\n", params.verbose_prompt ? "true" : "false"); +} |