root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

llama : rename jina tokenizers to v2 (#7249)

Browse Source 
* refactor: rename jina tokenizers to v2

* refactor: keep refactoring non-breaking
This commit is contained in:
Joan Fontanals 2024-05-13 10:35:14 +02:00 committed by GitHub
parent b1f8af1886
commit 9aa672490c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
convert-hf-to-gguf-update.py
View File

@ -74,9 +74,9 @@ models = [
{"name": "qwen2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
{"name": "olmo", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
{"name": "dbrx", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
{"name": "jina-en", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
{"name": "jina-es", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
{"name": "jina-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
{"name": "jina-v2-en", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
{"name": "jina-v2-es", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
]
# make directory "models/tokenizers" if it doesn't exist

6
convert-hf-to-gguf.py
View File

@ -475,13 +475,13 @@ class Model:
res = "dbrx"
if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-en
res = "jina-en"
res = "jina-v2-en"
if chkhsh == "171aeeedd6fb548d418a7461d053f11b6f1f1fc9b387bd66640d28a4b9f5c643":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-es
res = "jina-es"
res = "jina-v2-es"
if chkhsh == "27949a2493fc4a9f53f5b9b029c82689cfbe5d3a1929bb25e043089e28466de6":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-de
res = "jina-de"
res = "jina-v2-de"
if res is None:
logger.warning("\n")

4
llama.cpp
View File

@ -4424,7 +4424,9 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "gpt-2" ||
tokenizer_pre == "jina-es" ||
tokenizer_pre == "jina-de") {
tokenizer_pre == "jina-de" ||
tokenizer_pre == "jina-v2-es" ||
tokenizer_pre == "jina-v2-de") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_GPT2;
} else if (
tokenizer_pre == "refact") {