vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-15 03:19:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

remove old filever checks (+7 squashed commit)

Browse source 
Squashed commit:

[b72627a] new format not working

[e568870] old ver works

[7053b77] compile errors fixed, fixing linkers

[4ae8889] add new ver

[ff82dfd] file format checks

[25b8aa8] refactoring type names

[931063b] still merging
This commit is contained in:
Concedo 2023-05-20 16:47:44 +08:00
parent 417302b226
commit c048bcfec4
25 changed files with 3180 additions and 506 deletions
Download patch file Download diff file Expand all files Collapse all files

9
otherarch/gpt2_v2.cpp
View file

@ -15,12 +15,9 @@
#include "model_adapter.h"
#if defined(GGML_USE_CLBLAST)
#include "ggml_v2-opencl.h"
#endif
// load the model's weights from a file
ModelLoadResult gpt2_model_load(const std::string & fname, gpt2_model & model, gpt_vocab & vocab, FileFormat file_format, int gpulayers) {
ModelLoadResult gpt2_v2_model_load(const std::string & fname, gpt2_v2_model & model, gpt_vocab & vocab, FileFormat file_format, int gpulayers) {
printf("%s: loading model from '%s'\n", __func__, fname.c_str());
auto fin = std::ifstream(fname, std::ios::binary);
@ -379,8 +376,8 @@ ModelLoadResult gpt2_model_load(const std::string & fname, gpt2_model & model, g
// - embd_inp: the embeddings of the tokens in the context
// - embd_w: the predicted logits for the next token
//
bool gpt2_eval(
const gpt2_model & model,
bool gpt2_v2_eval(
const gpt2_v2_model & model,
const int n_threads,
const int n_past,
const std::vector<gpt_vocab::id> & embd_inp,