Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 05:48:47 +01:00
Code Issues Packages Projects Releases Wiki Activity

common : YAYF (yet another YARN fix) (#3925)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2023-11-03 09:24:00 +02:00 committed by GitHub
parent 3fdbe6b66b
commit 05816027d6
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 27 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
common/common.h
View File

@ -61,9 +61,9 @@ struct gpt_params {
int32_t n_beams = 0; // if non-zero then use beam search of given width. int32_t n_beams = 0; // if non-zero then use beam search of given width.
float rope_freq_base = 0.0f; // RoPE base frequency float rope_freq_base = 0.0f; // RoPE base frequency
float rope_freq_scale = 0.0f; // RoPE frequency scaling factor float rope_freq_scale = 0.0f; // RoPE frequency scaling factor
float yarn_ext_factor = NAN; // YaRN extrapolation mix factor float yarn_ext_factor = -1.0f; // YaRN extrapolation mix factor
float yarn_attn_factor = 1.0f; // YaRN magnitude scaling factor float yarn_attn_factor = 1.0f; // YaRN magnitude scaling factor
float yarn_beta_fast = 32.0f;// YaRN low correction dim float yarn_beta_fast = 32.0f; // YaRN low correction dim
float yarn_beta_slow = 1.0f; // YaRN high correction dim float yarn_beta_slow = 1.0f; // YaRN high correction dim
int32_t yarn_orig_ctx = 0; // YaRN original context length int32_t yarn_orig_ctx = 0; // YaRN original context length
int8_t rope_scaling_type = LLAMA_ROPE_SCALING_UNSPECIFIED; int8_t rope_scaling_type = LLAMA_ROPE_SCALING_UNSPECIFIED;