tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 16:23:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : gemma3n text-only (#14400)

Browse Source 
* gemma3n

* add llm_graph_input_one
This commit is contained in:
Xuan-Son Nguyen
2025-06-26 19:34:02 +02:00
committed by GitHub
parent a01047b041
commit 8846aace49
13 changed files with 960 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llama-hparams.h
View File

@@ -143,6 +143,12 @@ struct llama_hparams {
uint32_t n_attn_temp_floor_scale = 8192;
float f_attn_temp_scale = 0.1;
// gemma3n altup
uint32_t n_altup = 4; // altup_num_inputs
uint32_t i_altup_act = 0; // altup_active_idx
uint32_t laurel_rank = 64;
uint32_t n_embd_altup = 256;
// needed by encoder-decoder models (e.g. T5, FLAN-T5)
// ref: https://github.com/ggerganov/llama.cpp/pull/8141
llama_token dec_start_token_id = LLAMA_TOKEN_NULL;