.. |
__init__.py
|
05faa0b3c8
add quantization script for cpu
|
3 年之前 |
config.json
|
a798ea04a6
add minimalistic benchmarks
|
3 年之前 |
convert_model.py
|
6047a2ffe0
push config and tokenizer separately
|
3 年之前 |
inference_one_block.py
|
e8241d2915
black everything
|
3 年之前 |
run_server.py
|
1ab5fb1630
fetch a specific bloom block without downloading the entire model
|
3 年之前 |