root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

llama : print help to stdout (#2338)

Browse Source
This commit is contained in:
maddes8cht 2023-07-23 13:59:48 +02:00 committed by GitHub
parent bc3ec2cdc9
commit 1d0824b247
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 79 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

158
examples/common.cpp
View File

@ -458,91 +458,91 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
} }
void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
fprintf(stderr, "usage: %s [options]\n", argv[0]); fprintf(stdout, "usage: %s [options]\n", argv[0]);
fprintf(stderr, "\n"); fprintf(stdout, "\n");
fprintf(stderr, "options:\n"); fprintf(stdout, "options:\n");
fprintf(stderr, " -h, --help show this help message and exit\n"); fprintf(stdout, " -h, --help show this help message and exit\n");
fprintf(stderr, " -i, --interactive run in interactive mode\n"); fprintf(stdout, " -i, --interactive run in interactive mode\n");
fprintf(stderr, " --interactive-first run in interactive mode and wait for input right away\n"); fprintf(stdout, " --interactive-first run in interactive mode and wait for input right away\n");
fprintf(stderr, " -ins, --instruct run in instruction mode (use with Alpaca models)\n"); fprintf(stdout, " -ins, --instruct run in instruction mode (use with Alpaca models)\n");
fprintf(stderr, " --multiline-input allows you to write or paste multiple lines without ending each in '\\'\n"); fprintf(stdout, " --multiline-input allows you to write or paste multiple lines without ending each in '\\'\n");
fprintf(stderr, " -r PROMPT, --reverse-prompt PROMPT\n"); fprintf(stdout, " -r PROMPT, --reverse-prompt PROMPT\n");
fprintf(stderr, " halt generation at PROMPT, return control in interactive mode\n"); fprintf(stdout, " halt generation at PROMPT, return control in interactive mode\n");
fprintf(stderr, " (can be specified more than once for multiple prompts).\n"); fprintf(stdout, " (can be specified more than once for multiple prompts).\n");
fprintf(stderr, " --color colorise output to distinguish prompt and user input from generations\n"); fprintf(stdout, " --color colorise output to distinguish prompt and user input from generations\n");
fprintf(stderr, " -s SEED, --seed SEED RNG seed (default: -1, use random seed for < 0)\n"); fprintf(stdout, " -s SEED, --seed SEED RNG seed (default: -1, use random seed for < 0)\n");
fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads);
fprintf(stderr, " -p PROMPT, --prompt PROMPT\n"); fprintf(stdout, " -p PROMPT, --prompt PROMPT\n");
fprintf(stderr, " prompt to start generation with (default: empty)\n"); fprintf(stdout, " prompt to start generation with (default: empty)\n");
fprintf(stderr, " -e process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n"); fprintf(stdout, " -e process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n");
fprintf(stderr, " --prompt-cache FNAME file to cache prompt state for faster startup (default: none)\n"); fprintf(stdout, " --prompt-cache FNAME file to cache prompt state for faster startup (default: none)\n");
fprintf(stderr, " --prompt-cache-all if specified, saves user input and generations to cache as well.\n"); fprintf(stdout, " --prompt-cache-all if specified, saves user input and generations to cache as well.\n");
fprintf(stderr, " not supported with --interactive or other interactive options\n"); fprintf(stdout, " not supported with --interactive or other interactive options\n");
fprintf(stderr, " --prompt-cache-ro if specified, uses the prompt cache but does not update it.\n"); fprintf(stdout, " --prompt-cache-ro if specified, uses the prompt cache but does not update it.\n");
fprintf(stderr, " --random-prompt start with a randomized prompt.\n"); fprintf(stdout, " --random-prompt start with a randomized prompt.\n");
fprintf(stderr, " --in-prefix STRING string to prefix user inputs with (default: empty)\n"); fprintf(stdout, " --in-prefix STRING string to prefix user inputs with (default: empty)\n");
fprintf(stderr, " --in-suffix STRING string to suffix after user inputs with (default: empty)\n"); fprintf(stdout, " --in-suffix STRING string to suffix after user inputs with (default: empty)\n");
fprintf(stderr, " -f FNAME, --file FNAME\n"); fprintf(stdout, " -f FNAME, --file FNAME\n");
fprintf(stderr, " prompt file to start generation.\n"); fprintf(stdout, " prompt file to start generation.\n");
fprintf(stderr, " -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict); fprintf(stdout, " -n N, --n-predict N number of tokens to predict (default: %d, -1 = infinity)\n", params.n_predict);
fprintf(stderr, " --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k); fprintf(stdout, " --top-k N top-k sampling (default: %d, 0 = disabled)\n", params.top_k);
fprintf(stderr, " --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p); fprintf(stdout, " --top-p N top-p sampling (default: %.1f, 1.0 = disabled)\n", (double)params.top_p);
fprintf(stderr, " --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z); fprintf(stdout, " --tfs N tail free sampling, parameter z (default: %.1f, 1.0 = disabled)\n", (double)params.tfs_z);
fprintf(stderr, " --typical N locally typical sampling, parameter p (default: %.1f, 1.0 = disabled)\n", (double)params.typical_p); fprintf(stdout, " --typical N locally typical sampling, parameter p (default: %.1f, 1.0 = disabled)\n", (double)params.typical_p);
fprintf(stderr, " --repeat-last-n N last n tokens to consider for penalize (default: %d, 0 = disabled, -1 = ctx_size)\n", params.repeat_last_n); fprintf(stdout, " --repeat-last-n N last n tokens to consider for penalize (default: %d, 0 = disabled, -1 = ctx_size)\n", params.repeat_last_n);
fprintf(stderr, " --repeat-penalty N penalize repeat sequence of tokens (default: %.1f, 1.0 = disabled)\n", (double)params.repeat_penalty); fprintf(stdout, " --repeat-penalty N penalize repeat sequence of tokens (default: %.1f, 1.0 = disabled)\n", (double)params.repeat_penalty);
fprintf(stderr, " --presence-penalty N repeat alpha presence penalty (default: %.1f, 0.0 = disabled)\n", (double)params.presence_penalty); fprintf(stdout, " --presence-penalty N repeat alpha presence penalty (default: %.1f, 0.0 = disabled)\n", (double)params.presence_penalty);
fprintf(stderr, " --frequency-penalty N repeat alpha frequency penalty (default: %.1f, 0.0 = disabled)\n", (double)params.frequency_penalty); fprintf(stdout, " --frequency-penalty N repeat alpha frequency penalty (default: %.1f, 0.0 = disabled)\n", (double)params.frequency_penalty);
fprintf(stderr, " --mirostat N use Mirostat sampling.\n"); fprintf(stdout, " --mirostat N use Mirostat sampling.\n");
fprintf(stderr, " Top K, Nucleus, Tail Free and Locally Typical samplers are ignored if used.\n"); fprintf(stdout, " Top K, Nucleus, Tail Free and Locally Typical samplers are ignored if used.\n");
fprintf(stderr, " (default: %d, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)\n", params.mirostat); fprintf(stdout, " (default: %d, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0)\n", params.mirostat);
fprintf(stderr, " --mirostat-lr N Mirostat learning rate, parameter eta (default: %.1f)\n", (double)params.mirostat_eta); fprintf(stdout, " --mirostat-lr N Mirostat learning rate, parameter eta (default: %.1f)\n", (double)params.mirostat_eta);
fprintf(stderr, " --mirostat-ent N Mirostat target entropy, parameter tau (default: %.1f)\n", (double)params.mirostat_tau); fprintf(stdout, " --mirostat-ent N Mirostat target entropy, parameter tau (default: %.1f)\n", (double)params.mirostat_tau);
fprintf(stderr, " -l TOKEN_ID(+/-)BIAS, --logit-bias TOKEN_ID(+/-)BIAS\n"); fprintf(stdout, " -l TOKEN_ID(+/-)BIAS, --logit-bias TOKEN_ID(+/-)BIAS\n");
fprintf(stderr, " modifies the likelihood of token appearing in the completion,\n"); fprintf(stdout, " modifies the likelihood of token appearing in the completion,\n");
fprintf(stderr, " i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',\n"); fprintf(stdout, " i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',\n");
fprintf(stderr, " or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'\n"); fprintf(stdout, " or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'\n");
fprintf(stderr, " --cfg-negative-prompt PROMPT \n"); fprintf(stdout, " --cfg-negative-prompt PROMPT \n");
fprintf(stderr, " negative prompt to use for guidance. (default: empty)\n"); fprintf(stdout, " negative prompt to use for guidance. (default: empty)\n");
fprintf(stderr, " --cfg-scale N strength of guidance (default: %f, 1.0 = disable)\n", params.cfg_scale); fprintf(stdout, " --cfg-scale N strength of guidance (default: %f, 1.0 = disable)\n", params.cfg_scale);
fprintf(stderr, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx); fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stderr, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base); fprintf(stdout, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base);
fprintf(stderr, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale); fprintf(stdout, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale);
fprintf(stderr, " --ignore-eos ignore end of stream token and continue generating (implies --logit-bias 2-inf)\n"); fprintf(stdout, " --ignore-eos ignore end of stream token and continue generating (implies --logit-bias 2-inf)\n");
fprintf(stderr, " --no-penalize-nl do not penalize newline token\n"); fprintf(stdout, " --no-penalize-nl do not penalize newline token\n");
fprintf(stderr, " --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n"); fprintf(stdout, " --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n");
fprintf(stderr, " not recommended: doubles context memory required and no measurable increase in quality\n"); fprintf(stdout, " not recommended: doubles context memory required and no measurable increase in quality\n");
fprintf(stderr, " --temp N temperature (default: %.1f)\n", (double)params.temp); fprintf(stdout, " --temp N temperature (default: %.1f)\n", (double)params.temp);
fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch); fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " --perplexity compute perplexity over each ctx window of the prompt\n"); fprintf(stdout, " --perplexity compute perplexity over each ctx window of the prompt\n");
fprintf(stderr, " --perplexity-lines compute perplexity over each line of the prompt\n"); fprintf(stdout, " --perplexity-lines compute perplexity over each line of the prompt\n");
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep); fprintf(stdout, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
fprintf(stderr, " --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks); fprintf(stdout, " --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);
if (llama_mlock_supported()) { if (llama_mlock_supported()) {
fprintf(stderr, " --mlock force system to keep model in RAM rather than swapping or compressing\n"); fprintf(stdout, " --mlock force system to keep model in RAM rather than swapping or compressing\n");
} }
if (llama_mmap_supported()) { if (llama_mmap_supported()) {
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n"); fprintf(stdout, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
} }
fprintf(stderr, " --numa attempt optimizations that help on some NUMA systems\n"); fprintf(stdout, " --numa attempt optimizations that help on some NUMA systems\n");
fprintf(stderr, " if run without this previously, it is recommended to drop the system page cache before using this\n"); fprintf(stdout, " if run without this previously, it is recommended to drop the system page cache before using this\n");
fprintf(stderr, " see https://github.com/ggerganov/llama.cpp/issues/1437\n"); fprintf(stdout, " see https://github.com/ggerganov/llama.cpp/issues/1437\n");
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD #ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
fprintf(stderr, " -ngl N, --n-gpu-layers N\n"); fprintf(stdout, " -ngl N, --n-gpu-layers N\n");
fprintf(stderr, " number of layers to store in VRAM\n"); fprintf(stdout, " number of layers to store in VRAM\n");
fprintf(stderr, " -ts SPLIT --tensor-split SPLIT\n"); fprintf(stdout, " -ts SPLIT --tensor-split SPLIT\n");
fprintf(stderr, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n"); fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
fprintf(stderr, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n" ); fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n" );
fprintf(stderr, " -lv, --low-vram don't allocate VRAM scratch buffer\n" ); fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n" );
#endif #endif
fprintf(stderr, " --mtest compute maximum memory usage\n"); fprintf(stdout, " --mtest compute maximum memory usage\n");
fprintf(stderr, " --export export the computation graph to 'llama.ggml'\n"); fprintf(stdout, " --export export the computation graph to 'llama.ggml'\n");
fprintf(stderr, " --verbose-prompt print prompt before generation\n"); fprintf(stdout, " --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n"); fprintf(stdout, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
fprintf(stderr, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n"); fprintf(stdout, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n");
fprintf(stderr, " -m FNAME, --model FNAME\n"); fprintf(stdout, " -m FNAME, --model FNAME\n");
fprintf(stderr, " model path (default: %s)\n", params.model.c_str()); fprintf(stdout, " model path (default: %s)\n", params.model.c_str());
fprintf(stderr, "\n"); fprintf(stdout, "\n");
} }
std::string gpt_random_prompt(std::mt19937 & rng) { std::string gpt_random_prompt(std::mt19937 & rng) {