vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/ISSUE_TEMPLATE/config.yml
#	.gitignore
#	CMakeLists.txt
#	CONTRIBUTING.md
#	Makefile
#	README.md
#	ci/run.sh
#	common/common.h
#	examples/main-cmake-pkg/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	models/ggml-vocab-bert-bge.gguf.inp
#	models/ggml-vocab-bert-bge.gguf.out
#	models/ggml-vocab-deepseek-coder.gguf.inp
#	models/ggml-vocab-deepseek-coder.gguf.out
#	models/ggml-vocab-deepseek-llm.gguf.inp
#	models/ggml-vocab-deepseek-llm.gguf.out
#	models/ggml-vocab-falcon.gguf.inp
#	models/ggml-vocab-falcon.gguf.out
#	models/ggml-vocab-gpt-2.gguf.inp
#	models/ggml-vocab-gpt-2.gguf.out
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	models/ggml-vocab-llama-spm.gguf.inp
#	models/ggml-vocab-llama-spm.gguf.out
#	models/ggml-vocab-mpt.gguf.inp
#	models/ggml-vocab-mpt.gguf.out
#	models/ggml-vocab-phi-3.gguf.inp
#	models/ggml-vocab-phi-3.gguf.out
#	models/ggml-vocab-starcoder.gguf.inp
#	models/ggml-vocab-starcoder.gguf.out
#	requirements.txt
#	requirements/requirements-convert_legacy_llama.txt
#	scripts/check-requirements.sh
#	scripts/pod-llama.sh
#	src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-rope.cpp
This commit is contained in:
Concedo 2024-07-06 00:25:10 +08:00
commit 5b605d03ea
85 changed files with 4095 additions and 941 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/common.h
View file

@ -95,6 +95,7 @@ struct gpt_params {
enum llama_split_mode split_mode = LLAMA_SPLIT_MODE_LAYER; // how to split the model across GPUs
enum llama_rope_scaling_type rope_scaling_type = LLAMA_ROPE_SCALING_TYPE_UNSPECIFIED;
enum llama_pooling_type pooling_type = LLAMA_POOLING_TYPE_UNSPECIFIED; // pooling type for embeddings
enum llama_attention_type attention_type = LLAMA_ATTENTION_TYPE_UNSPECIFIED; // attention type for embeddings
// sampling parameters
int32_t top_k = 40; // <= 0 to use vocab size
@ -475,5 +476,3 @@ void yaml_dump_string_multiline(FILE * stream, const char * prop_name, const cha
void yaml_dump_non_result_info(
FILE * stream, const gpt_params & params, const llama_context * lctx,
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc);