8 lines
170 B
Plaintext
8 lines
170 B
Plaintext
|
# GGUF Conversion & Inference
|
||
|
|
llama-cpp-python
|
||
|
|
sentencepiece
|
||
|
|
gguf
|
||
|
|
transformers>=4.45.0
|
||
|
|
protobuf
|
||
|
|
# Optional: For faster conversion on some architectures
|
||
|
|
numpy<2.0.0
|