vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/tools.sh
#	README.md
This commit is contained in:
Concedo 2023-06-04 11:07:07 +08:00
commit 2868fac676
2 changed files with 10 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert-pth-to-ggml.py
View file

@ -4,7 +4,9 @@ import argparse
import convert import convert
parser = argparse.ArgumentParser(description='Convert a LLaMA model checkpoint to a ggml compatible file') parser = argparse.ArgumentParser(
description="""[DEPRECATED - use `convert.py` instead]
Convert a LLaMA model checkpoint to a ggml compatible file""")
parser.add_argument('dir_model', help='directory containing the model checkpoint') parser.add_argument('dir_model', help='directory containing the model checkpoint')
parser.add_argument('ftype', help='file type (0: float32, 1: float16)', type=int, choices=[0, 1], default=1) parser.add_argument('ftype', help='file type (0: float32, 1: float16)', type=int, choices=[0, 1], default=1)
args = parser.parse_args() args = parser.parse_args()

13
examples/main/main.cpp
View file

@ -202,6 +202,13 @@ int main(int argc, char ** argv) {
} }
} }
// if we will use the cache for the full prompt without reaching the end of the cache, force
// reevaluation of the last token token to recalculate the cached logits
if (!embd_inp.empty() && n_matching_session_tokens == embd_inp.size() &&
session_tokens.size() > embd_inp.size()) {
session_tokens.resize(embd_inp.size() - 1);
}
// number of tokens to keep when resetting context // number of tokens to keep when resetting context
if (params.n_keep < 0 || params.n_keep > (int) embd_inp.size() || params.instruct) { if (params.n_keep < 0 || params.n_keep > (int) embd_inp.size() || params.instruct) {
params.n_keep = (int)embd_inp.size(); params.n_keep = (int)embd_inp.size();
@ -360,12 +367,6 @@ int main(int argc, char ** argv) {
} }
} }
if (i > 0) { if (i > 0) {
// check if we've used up all the prompt but not all cached tokens
if (embd.size() == i && n_session_consumed < (int) session_tokens.size()) {
// force revaluation of the last token to recalculate logits
i--;
n_past--;
}
embd.erase(embd.begin(), embd.begin() + i); embd.erase(embd.begin(), embd.begin() + i);
} }
} }