mirror of
https://github.com/ollama/ollama.git
synced 2025-11-10 17:48:11 +01:00
4987f13d34
* feat: Bump llama.cpp to df1b612 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(mtmd): Correctly encode text chunks during mtmd tokenization There can be text chunks that appear interspersed with the image embeddings that contain template delimiter tokens for some models. These need to be correctly translated to text tokens. Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * tests: Use MtmdChunk in image_test Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * style: Fix unnecessary conversion linting Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix(ggml): Revert changes to ggml_hip.cpp These changes were done largely by our code assistant and are likely wrong Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Revert changes in mem_nvml.cpp Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update sync point to 1deee0 This brings in several more optimization commits and model support for EmbeddingGemma Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches for 1deee0 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: sync for bump to 1deee0 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Bad patch updates with errant `+` Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Bump llama.cpp/ggml to 7049736 Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: format-patches after latest bump Branch: LlamaCPPBump-GraniteDocling Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
44 lines
2.3 KiB
Diff
44 lines
2.3 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Michael Yang <mxyng@pm.me>
|
|
Date: Mon, 16 Sep 2024 15:53:13 -0700
|
|
Subject: [PATCH] pretokenizer
|
|
|
|
allow for an unset pretokenizer with a warning in the
|
|
logs instead of throwing an error
|
|
---
|
|
src/llama-vocab.cpp | 14 +++-----------
|
|
1 file changed, 3 insertions(+), 11 deletions(-)
|
|
|
|
diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
|
|
index 7fffd171..0b6edaf4 100644
|
|
--- a/src/llama-vocab.cpp
|
|
+++ b/src/llama-vocab.cpp
|
|
@@ -1812,16 +1812,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|
|
if (type == LLAMA_VOCAB_TYPE_BPE) {
|
|
add_space_prefix = false;
|
|
clean_spaces = true;
|
|
- if (tokenizer_pre.empty()) {
|
|
- LLAMA_LOG_WARN("%s: missing pre-tokenizer type, using: 'default'\n", __func__);
|
|
- LLAMA_LOG_WARN("%s: \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: GENERATION QUALITY WILL BE DEGRADED! \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: CONSIDER REGENERATING THE MODEL \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: ************************************ \n", __func__);
|
|
- LLAMA_LOG_WARN("%s: \n", __func__);
|
|
- pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
- } else if (tokenizer_pre == "default") {
|
|
+ if (tokenizer_pre == "default") {
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
} else if (
|
|
tokenizer_pre == "llama3" ||
|
|
@@ -1992,7 +1983,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_GROK_2;
|
|
clean_spaces = false;
|
|
} else {
|
|
- throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
|
|
+ LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__);
|
|
+ pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|
|
}
|
|
} else if (type == LLAMA_VOCAB_TYPE_SPM) {
|
|
pre_type = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
|