extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-17 08:01:51 +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

5
examples/talk-llama/llama-arch.h
View File

@ -151,6 +151,7 @@ enum llm_kv {
LLM_KV_ATTENTION_SCALE,
LLM_KV_ATTENTION_KEY_LENGTH_MLA,
LLM_KV_ATTENTION_VALUE_LENGTH_MLA,
LLM_KV_ATTENTION_LAYER_INDICES,
LLM_KV_ROPE_DIMENSION_COUNT,
LLM_KV_ROPE_DIMENSION_SECTIONS,
@ -193,6 +194,7 @@ enum llm_kv {
LLM_KV_TOKENIZER_MASK_ID,
LLM_KV_TOKENIZER_ADD_BOS,
LLM_KV_TOKENIZER_ADD_EOS,
LLM_KV_TOKENIZER_ADD_SEP,
LLM_KV_TOKENIZER_ADD_PREFIX,
LLM_KV_TOKENIZER_REMOVE_EXTRA_WS,
LLM_KV_TOKENIZER_PRECOMPILED_CHARSMAP,
@ -439,3 +441,6 @@ const char * llm_arch_name(llm_arch arch);
llm_arch llm_arch_from_string(const std::string & name);
const llm_tensor_info & llm_tensor_info_for(llm_tensor tensor);
bool llm_arch_is_recurrent(const llm_arch & arch);
bool llm_arch_is_hybrid (const llm_arch & arch);