diff options
Diffstat (limited to 'examples/common.h')
| -rw-r--r-- | examples/common.h | 21 |
1 files changed, 15 insertions, 6 deletions
diff --git a/examples/common.h b/examples/common.h index 9d3697d7..14e6b1ba 100644 --- a/examples/common.h +++ b/examples/common.h @@ -8,6 +8,7 @@ #include <vector> #include <random> #include <thread> +#include <unordered_map> // // CLI argument parsing @@ -17,17 +18,25 @@ struct gpt_params { int32_t seed = -1; // RNG seed int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency()); int32_t n_predict = 128; // new tokens to predict - int32_t repeat_last_n = 64; // last n tokens to penalize int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions) int32_t n_ctx = 512; // context size int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS) int32_t n_keep = 0; // number of tokens to keep from initial prompt // sampling parameters - int32_t top_k = 40; - float top_p = 0.95f; - float temp = 0.80f; - float repeat_penalty = 1.10f; + std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens + int32_t top_k = 0; // <= 0 to use vocab size + float top_p = 1.0f; // 1.0 = disabled + float tfs_z = 1.0f; // 1.0 = disabled + float typical_p = 1.0f; // 1.0 = disabled + float temp = 1.0f; // 1.0 = disabled + float repeat_penalty = 1.0f; // 1.0 = disabled + int32_t repeat_last_n = -1; // last n tokens to penalize (0 = disable penalty, -1 = context size) + float frequency_penalty = 0.0f; // 0.0 = disabled + float presence_penalty = 0.0f; // 0.0 = disabled + int mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0 + float mirostat_tau = 5.0f; // target entropy + float mirostat_eta = 0.1f; // learning rate std::string model = "models/lamma-7B/ggml-model.bin"; // model path std::string prompt = ""; @@ -47,7 +56,7 @@ struct gpt_params { bool interactive_first = false; // wait for user input immediately bool instruct = false; // instruction mode (used for Alpaca models) - bool ignore_eos = false; // do not stop generating after eos + bool penalize_nl = true; // consider newlines as a repeatable token bool perplexity = false; // compute perplexity over the prompt bool use_mmap = true; // use mmap for faster loads bool use_mlock = false; // use mlock to keep model in memory |