root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

common : change default parameters to pre-#1126 (#1223)

Browse Source
This commit is contained in:
Georgi Gerganov 2023-04-29 09:51:06 +03:00 committed by GitHub
parent dd7eff57d8
commit 334637e43e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
examples/common.h
View File

@ -17,7 +17,7 @@
struct gpt_params { struct gpt_params {
int32_t seed = -1; // RNG seed int32_t seed = -1; // RNG seed
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency()); int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 128; // new tokens to predict int32_t n_predict = -1; // new tokens to predict
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions) int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size 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_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
@ -25,18 +25,18 @@ struct gpt_params {
// sampling parameters // sampling parameters
std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens
int32_t top_k = 0; // <= 0 to use vocab size int32_t top_k = 40; // <= 0 to use vocab size
float top_p = 1.0f; // 1.0 = disabled float top_p = 0.95f; // 1.0 = disabled
float tfs_z = 1.0f; // 1.0 = disabled float tfs_z = 1.00f; // 1.0 = disabled
float typical_p = 1.0f; // 1.0 = disabled float typical_p = 1.00f; // 1.0 = disabled
float temp = 1.0f; // 1.0 = disabled float temp = 0.80f; // 1.0 = disabled
float repeat_penalty = 1.0f; // 1.0 = disabled float repeat_penalty = 1.10f; // 1.0 = disabled
int32_t repeat_last_n = -1; // last n tokens to penalize (0 = disable penalty, -1 = context size) int32_t repeat_last_n = 64; // last n tokens to penalize (0 = disable penalty, -1 = context size)
float frequency_penalty = 0.0f; // 0.0 = disabled float frequency_penalty = 0.00f; // 0.0 = disabled
float presence_penalty = 0.0f; // 0.0 = disabled float presence_penalty = 0.00f; // 0.0 = disabled
int mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0 int mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0
float mirostat_tau = 5.0f; // target entropy float mirostat_tau = 5.00f; // target entropy
float mirostat_eta = 0.1f; // learning rate float mirostat_eta = 0.10f; // learning rate
std::string model = "models/lamma-7B/ggml-model.bin"; // model path std::string model = "models/lamma-7B/ggml-model.bin"; // model path
std::string prompt = ""; std::string prompt = "";