vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 09:04:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

adjust lite default port, disable double BOS warning, whisper and SD go quiet when horde mode is set too

Browse source
This commit is contained in:
Concedo 2024-06-13 15:10:35 +08:00
parent 92bbebb357
commit 49e4c3fd7b
3 changed files with 12 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
klite.embd
View file

@ -3732,7 +3732,7 @@ Current version: 146
var temp_scenario = null;
var last_token_budget = ""; //to display token limits
var last_known_filename = "saved_story.json";
var localmodeport = 5000;
var localmodeport = 5001;
var localmodehost = "localhost";
var sublocalpathname = "";
var localmodekey = "";

6
koboldcpp.py
View file

@ -599,7 +599,7 @@ def sd_generate(genparams):
height = tryparseint(genparams.get("height", 512))
seed = tryparseint(genparams.get("seed", -1))
sample_method = genparams.get("sampler_name", "k_euler_a")
is_quiet = True if args.quiet else False
is_quiet = True if (args.quiet or args.debugmode == -1) else False
clip_skip = tryparseint(genparams.get("clip_skip", -1))
#clean vars
@ -656,7 +656,7 @@ def whisper_load_model(model_filename):
def whisper_generate(genparams):
global args
is_quiet = True if args.quiet else False
is_quiet = True if (args.quiet or args.debugmode == -1) else False
prompt = genparams.get("prompt", "")
audio_data = genparams.get("audio_data", "")
if audio_data.startswith("data:audio"):
@ -672,7 +672,7 @@ def whisper_generate(genparams):
return outstr
def utfprint(str):
maxlen = 20000
maxlen = 25000
strlength = len(str)
if strlength > maxlen: #limit max output len
str = str[:maxlen] + f"... (+{strlength-maxlen} chars)"

16
llama.cpp
View file

@ -13781,10 +13781,10 @@ static std::vector<llama_vocab::id> llama_tokenize_internal(const llama_vocab &
}
if (add_special && vocab.special_add_bos != 0 && output.size() >= 2 && output[1] == vocab.special_bos_id) {
LLAMA_LOG_WARN(
"%s: Added a BOS token to the prompt as specified by the model but the prompt "
"also starts with a BOS token. So now the final prompt starts with 2 BOS tokens. "
"Are you sure this is what you want?\n", __FUNCTION__);
// LLAMA_LOG_WARN(
// "%s: Added a BOS token to the prompt as specified by the model but the prompt "
// "also starts with a BOS token. So now the final prompt starts with 2 BOS tokens. "
// "Are you sure this is what you want?\n", __FUNCTION__);
}
if (add_special && vocab.special_add_eos == 1) {
@ -13824,10 +13824,10 @@ static std::vector<llama_vocab::id> llama_tokenize_internal(const llama_vocab &
}
if (add_special && vocab.special_add_bos != 0 && output.size() >= 2 && output[1] == vocab.special_bos_id) {
LLAMA_LOG_WARN(
"%s: Added a BOS token to the prompt as specified by the model but the prompt "
"also starts with a BOS token. So now the final prompt starts with 2 BOS tokens. "
"Are you sure this is what you want?\n", __FUNCTION__);
// LLAMA_LOG_WARN(
// "%s: Added a BOS token to the prompt as specified by the model but the prompt "
// "also starts with a BOS token. So now the final prompt starts with 2 BOS tokens. "
// "Are you sure this is what you want?\n", __FUNCTION__);
}
if (add_special && vocab.special_add_eos == 1) {