furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 10:15:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add support for BERT embedding models (#5423)

Browse Source 
* BERT model graph construction (build_bert)
* WordPiece tokenizer (llm_tokenize_wpm)
* Add flag for non-causal attention models
* Allow for models that only output embeddings
* Support conversion of BERT models to GGUF
* Based on prior work by @xyzhang626 and @skeskinen

---------

Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Douglas Hanley
2024-02-11 11:21:38 -05:00
committed by GitHub
co-authored by Jared Van Bortel Jared Van Bortel Georgi Gerganov
parent 97a336507e
commit 2891c8aa9a
8 changed files with 616 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.flake8
+1
View File
@@ -1,2 +1,3 @@
[flake8]
max-line-length = 125
ignore = W503