forked from ollama/ollama
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
) This reverts commit 6920964.
- Loading branch information
Showing
1 changed file
with
1 addition
and
1 deletion.
There are no files selected for viewing
Submodule llama.cpp
updated
19 files
+8 −0 | Makefile | |
+46 −0 | ci/run.sh | |
+79 −39 | convert-hf-to-gguf.py | |
+1 −0 | examples/CMakeLists.txt | |
+106 −36 | examples/embedding/embedding.cpp | |
+3 −3 | examples/finetune/README.md | |
+121 −121 | examples/finetune/finetune.cpp | |
+27 −27 | examples/train-text-from-scratch/train-text-from-scratch.cpp | |
+18 −18 | ggml-quants.c | |
+45 −0 | gguf-py/examples/reader.py | |
+37 −20 | gguf-py/gguf/constants.py | |
+3 −0 | gguf-py/gguf/gguf_writer.py | |
+10 −2 | gguf-py/gguf/tensor_mapping.py | |
+240 −85 | llama.cpp | |
+5 −0 | llama.h | |
+2 −3 | tests/test-backend-ops.cpp | |
+37 −36 | tests/test-tokenizer-1-bpe.cpp | |
+29 −22 | tests/test-tokenizer-1-llama.cpp | |
+42 −30 | unicode.h |