mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-06-17 14:28:07 +00:00
talk-llama : sync llama.cpp
This commit is contained in:
@ -179,6 +179,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
|
||||
{ LLM_KV_TOKENIZER_HF_JSON, "tokenizer.huggingface.json" },
|
||||
{ LLM_KV_TOKENIZER_RWKV, "tokenizer.rwkv.world" },
|
||||
{ LLM_KV_TOKENIZER_CHAT_TEMPLATE, "tokenizer.chat_template" },
|
||||
{ LLM_KV_TOKENIZER_CHAT_TEMPLATE_N, "tokenizer.chat_template.%s" },
|
||||
{ LLM_KV_TOKENIZER_FIM_PRE_ID, "tokenizer.ggml.fim_pre_token_id" },
|
||||
{ LLM_KV_TOKENIZER_FIM_SUF_ID, "tokenizer.ggml.fim_suf_token_id" },
|
||||
{ LLM_KV_TOKENIZER_FIM_MID_ID, "tokenizer.ggml.fim_mid_token_id" },
|
||||
@ -1023,6 +1024,9 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
|
||||
{ LLM_TENSOR_OUTPUT, "output" },
|
||||
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
|
||||
{ LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" },
|
||||
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
|
||||
{ LLM_TENSOR_ATTN_K, "blk.%d.attn_k" },
|
||||
{ LLM_TENSOR_ATTN_V, "blk.%d.attn_v" },
|
||||
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
|
||||
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
|
||||
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
|
||||
@ -1443,10 +1447,11 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
|
||||
{LLM_TENSOR_CONVNEXT_GAMMA, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
|
||||
};
|
||||
|
||||
LLM_KV::LLM_KV(llm_arch arch) : arch(arch) {}
|
||||
LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {}
|
||||
|
||||
std::string LLM_KV::operator()(llm_kv kv) const {
|
||||
return ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch));
|
||||
return suffix ? ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch), suffix)
|
||||
: ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch));
|
||||
}
|
||||
|
||||
std::string LLM_TN_IMPL::str() const {
|
||||
|
Reference in New Issue
Block a user