From 49e4c3fd7b2a47f16cb9c8d2ee4dd829656c45c4 Mon Sep 17 00:00:00 2001 From: Concedo <39025047+LostRuins@users.noreply.github.com> Date: Thu, 13 Jun 2024 15:10:35 +0800 Subject: [PATCH] adjust lite default port, disable double BOS warning, whisper and SD go quiet when horde mode is set too --- klite.embd | 2 +- koboldcpp.py | 6 +++--- llama.cpp | 16 ++++++++-------- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/klite.embd b/klite.embd index 85f10e0a1..81003b4bc 100644 --- a/klite.embd +++ b/klite.embd @@ -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 = ""; diff --git a/koboldcpp.py b/koboldcpp.py index 43f062eda..55257ccc2 100644 --- a/koboldcpp.py +++ b/koboldcpp.py @@ -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)" diff --git a/llama.cpp b/llama.cpp index d58a38a95..6dea3c424 100644 --- a/llama.cpp +++ b/llama.cpp @@ -13781,10 +13781,10 @@ static std::vector 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_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) {