Francis Couture-Harpin 7ef4254a92 ggml-quants : faster 1.625 bpw AVX2 vec_dot ...

Not using a lookup table anymore makes it match q4_0 speed.

* gguf-py : fix formatting

* llama : remove spaces on empty line

2024-06-27 02:06:28 -04:00

..

__init__.py

convert-hf : support direct Q8_0 conversion (#7234)

2024-05-13 14:10:51 -04:00

constants.py

ggml-quants : 1.625 bpw ternary packing for BitNet 1.58b

2024-06-27 02:06:22 -04:00

gguf_reader.py

Gguf dump start data offset via --data-offset and some extra refactor (#8054)

2024-06-25 22:03:25 +10:00

gguf_writer.py

Option to split during conversion (#6942)

2024-06-24 19:42:03 +10:00

gguf.py

gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)

2023-11-11 08:04:50 +03:00

lazy.py

convert-hf : support direct Q8_0 conversion (#7234)

2024-05-13 14:10:51 -04:00

py.typed

convert : various script cleanups/fixes + merges and special token handling (#2842)

2023-08-30 11:25:50 +03:00

quants.py

ggml-quants : faster 1.625 bpw AVX2 vec_dot

2024-06-27 02:06:28 -04:00

tensor_mapping.py

gguf-py, convert-hf : model conversion support for T5 and FLAN-T5 model variants (#5763)

2024-06-24 07:06:05 +02:00

vocab.py

Move convert.py to examples/convert-legacy-llama.py (#7430)

2024-05-30 21:40:00 +10:00