vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo

Browse source 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	README.md
#	flake.nix
This commit is contained in:
Concedo 2023-04-14 21:40:33 +08:00
commit a819f22cac
26 changed files with 1657 additions and 1390 deletions
Download patch file Download diff file Expand all files Collapse all files

6
model_adapter.cpp
View file

@ -227,13 +227,13 @@ void print_tok_vec(std::vector<float> &embd)
void ContextFastForward(std::vector<int> &current_context_tokens, std::vector<int> &embd_inp,
int &n_past, std::vector<int> &last_n_tokens, const int nctx, std::vector<int> &smartcontext, bool useSmartContext)
{
const int SCTokThreshold = 32; //how many tokens of similarity triggers smartcontext
{
const int SCCtxLenThreshold = nctx * 0.8; //how much context length must be reach to trigger smartcontext
const int SCInpLenThreshold = nctx * 0.6; //how big must the input array be to trigger smartcontext
const int SCPastLenThreshold = nctx * 0.5; //how wide of a gap between the fast forwarded past and the present to trigger smart context
const float SCTruncationRatio = 0.5; //ratio for how many tokens to fast forward
const int SCTokThreshold = 32 + (nctx*0.05); //how many tokens of similarity triggers smartcontext
// printf("\nORIGINAL CTX:\n");
// print_tok_vec(current_context_tokens);
// printf("\nORIGINAL EMBD:\n");