extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-16 11:58:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-20 21:18:44 +03:00
parent d65a579a0a
commit e6c10cf3d5
28 changed files with 2521 additions and 1738 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/talk-llama/llama-hparams.h
View File

@ -115,6 +115,9 @@ struct llama_hparams {
uint32_t ssm_d_state = 0;
uint32_t ssm_dt_rank = 0;
// for hybrid state space models
std::array<bool, LLAMA_MAX_LAYERS> recurrent_layer_arr;
bool ssm_dt_b_c_rms = false;
float f_clamp_kqv = 0.0f;
@ -181,10 +184,15 @@ struct llama_hparams {
// dimension of the rolling state embeddings
// corresponds to Mamba's conv_states size or RWKV's token_shift states size
uint32_t n_embd_k_s() const;
uint32_t n_embd_r() const;
// dimension of the recurrent state embeddings
uint32_t n_embd_v_s() const;
uint32_t n_embd_s() const;
// whether or not the given layer is recurrent (for hybrid models)
bool is_recurrent(uint32_t il) const;
uint32_t n_pos_per_embd() const;
bool is_swa(uint32_t il) const;
};