mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-14 02:49:41 +00:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .devops/intel.Dockerfile # CMakeLists.txt # README.md # common/CMakeLists.txt # docs/multimodal.md # ggml/src/CMakeLists.txt # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-metal/CMakeLists.txt # ggml/src/ggml-sycl/CMakeLists.txt # ggml/src/ggml-sycl/common.hpp # ggml/src/ggml-sycl/cpy.cpp # ggml/src/ggml-sycl/gemm.hpp # ggml/src/ggml-sycl/ggml-sycl.cpp # src/llama-context.cpp
This commit is contained in:
Concedo
commit
5f9e96e82d
18 changed files with 505 additions and 247 deletions
|
|
@ -9,18 +9,18 @@
|
|||
|
||||
#include <algorithm>
|
||||
#include <cassert>
|
||||
#include <cctype>
|
||||
#include <cfloat>
|
||||
#include <climits>
|
||||
#include <cstdarg>
|
||||
#include <cstring>
|
||||
#include <forward_list>
|
||||
#include <limits>
|
||||
#include <map>
|
||||
#include <queue>
|
||||
#include <sstream>
|
||||
#include <regex>
|
||||
#include <set>
|
||||
#include <unordered_map>
|
||||
#include <cctype>
|
||||
|
||||
//
|
||||
// helpers
|
||||
|
|
@ -2848,6 +2848,10 @@ int32_t llama_vocab::impl::token_to_piece(llama_token token, char * buf, int32_t
|
|||
// copy piece chars to output text buffer
|
||||
// skip up to 'lstrip' leading spaces before copying
|
||||
auto _try_copy = [=] (const char * token, size_t size) -> int32_t {
|
||||
if (size >= static_cast<size_t>(std::numeric_limits<int32_t>::max())) {
|
||||
GGML_ABORT("invalid token size: %zu exceeds int32_t limit", size);
|
||||
}
|
||||
|
||||
for (int32_t i = 0; i < lstrip && size && *token == ' '; ++i) {
|
||||
token++;
|
||||
size--;
|
||||
|
|
@ -3044,26 +3048,26 @@ void llama_vocab::impl::print_info() const {
|
|||
LLAMA_LOG_INFO("%s: n_merges = %u\n", __func__, (uint32_t) bpe_ranks.size());
|
||||
|
||||
// special tokens
|
||||
if (special_bos_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: BOS token = %d '%s'\n", __func__, special_bos_id, id_to_token[special_bos_id].text.c_str() ); }
|
||||
if (special_eos_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOS token = %d '%s'\n", __func__, special_eos_id, id_to_token[special_eos_id].text.c_str() ); }
|
||||
if (special_eot_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOT token = %d '%s'\n", __func__, special_eot_id, id_to_token[special_eot_id].text.c_str() ); }
|
||||
if (special_eom_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOM token = %d '%s'\n", __func__, special_eom_id, id_to_token[special_eom_id].text.c_str() ); }
|
||||
if (special_unk_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: UNK token = %d '%s'\n", __func__, special_unk_id, id_to_token[special_unk_id].text.c_str() ); }
|
||||
if (special_sep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: SEP token = %d '%s'\n", __func__, special_sep_id, id_to_token[special_sep_id].text.c_str() ); }
|
||||
if (special_pad_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: PAD token = %d '%s'\n", __func__, special_pad_id, id_to_token[special_pad_id].text.c_str() ); }
|
||||
if (special_mask_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: MASK token = %d '%s'\n", __func__, special_mask_id, id_to_token[special_mask_id].text.c_str() ); }
|
||||
if (special_bos_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: BOS token = %d '%s'\n", __func__, special_bos_id, id_to_token.at(special_bos_id).text.c_str() ); }
|
||||
if (special_eos_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOS token = %d '%s'\n", __func__, special_eos_id, id_to_token.at(special_eos_id).text.c_str() ); }
|
||||
if (special_eot_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOT token = %d '%s'\n", __func__, special_eot_id, id_to_token.at(special_eot_id).text.c_str() ); }
|
||||
if (special_eom_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: EOM token = %d '%s'\n", __func__, special_eom_id, id_to_token.at(special_eom_id).text.c_str() ); }
|
||||
if (special_unk_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: UNK token = %d '%s'\n", __func__, special_unk_id, id_to_token.at(special_unk_id).text.c_str() ); }
|
||||
if (special_sep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: SEP token = %d '%s'\n", __func__, special_sep_id, id_to_token.at(special_sep_id).text.c_str() ); }
|
||||
if (special_pad_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: PAD token = %d '%s'\n", __func__, special_pad_id, id_to_token.at(special_pad_id).text.c_str() ); }
|
||||
if (special_mask_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: MASK token = %d '%s'\n", __func__, special_mask_id, id_to_token.at(special_mask_id).text.c_str() ); }
|
||||
|
||||
if (linefeed_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: LF token = %d '%s'\n", __func__, linefeed_id, id_to_token[linefeed_id].text.c_str() ); }
|
||||
if (linefeed_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: LF token = %d '%s'\n", __func__, linefeed_id, id_to_token.at(linefeed_id).text.c_str() ); }
|
||||
|
||||
if (special_fim_pre_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM PRE token = %d '%s'\n", __func__, special_fim_pre_id, id_to_token[special_fim_pre_id].text.c_str() ); }
|
||||
if (special_fim_suf_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM SUF token = %d '%s'\n", __func__, special_fim_suf_id, id_to_token[special_fim_suf_id].text.c_str() ); }
|
||||
if (special_fim_mid_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM MID token = %d '%s'\n", __func__, special_fim_mid_id, id_to_token[special_fim_mid_id].text.c_str() ); }
|
||||
if (special_fim_pad_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM PAD token = %d '%s'\n", __func__, special_fim_pad_id, id_to_token[special_fim_pad_id].text.c_str() ); }
|
||||
if (special_fim_rep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM REP token = %d '%s'\n", __func__, special_fim_rep_id, id_to_token[special_fim_rep_id].text.c_str() ); }
|
||||
if (special_fim_sep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM SEP token = %d '%s'\n", __func__, special_fim_sep_id, id_to_token[special_fim_sep_id].text.c_str() ); }
|
||||
if (special_fim_pre_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM PRE token = %d '%s'\n", __func__, special_fim_pre_id, id_to_token.at(special_fim_pre_id).text.c_str() ); }
|
||||
if (special_fim_suf_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM SUF token = %d '%s'\n", __func__, special_fim_suf_id, id_to_token.at(special_fim_suf_id).text.c_str() ); }
|
||||
if (special_fim_mid_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM MID token = %d '%s'\n", __func__, special_fim_mid_id, id_to_token.at(special_fim_mid_id).text.c_str() ); }
|
||||
if (special_fim_pad_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM PAD token = %d '%s'\n", __func__, special_fim_pad_id, id_to_token.at(special_fim_pad_id).text.c_str() ); }
|
||||
if (special_fim_rep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM REP token = %d '%s'\n", __func__, special_fim_rep_id, id_to_token.at(special_fim_rep_id).text.c_str() ); }
|
||||
if (special_fim_sep_id != LLAMA_TOKEN_NULL) { LLAMA_LOG_INFO( "%s: FIM SEP token = %d '%s'\n", __func__, special_fim_sep_id, id_to_token.at(special_fim_sep_id).text.c_str() ); }
|
||||
|
||||
for (const auto & id : special_eog_ids) {
|
||||
LLAMA_LOG_INFO( "%s: EOG token = %d '%s'\n", __func__, id, id_to_token[id].text.c_str() );
|
||||
LLAMA_LOG_INFO( "%s: EOG token = %d '%s'\n", __func__, id, id_to_token.at(id).text.c_str() );
|
||||
}
|
||||
|
||||
LLAMA_LOG_INFO("%s: max token length = %d\n", __func__, max_token_len);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue