turboderp 5d5d57083e Increase quant tolerance slightly (for small Qwen2 models esp.)

2024-06-13 20:44:51 +02:00

..

standard_cal_data

Include calibration data

2023-12-08 20:20:43 +01:00

adaptivegptq.py

Update TODO: items

2024-05-18 06:43:27 +02:00

bot_status.py

Add machine-parseable output to convert script

2024-05-20 01:49:34 +02:00

compile.py

Add exit status code for quant error

2024-06-13 20:43:49 +02:00

measure.py

add layer GPU offloading for hidden/target states

2024-05-22 15:09:57 +09:00

optimize.py

Add machine-parseable output to convert script

2024-05-20 01:49:34 +02:00

qparams.py

Support for StarCoder2, initial

2024-03-05 21:20:29 +01:00

quantize.py

Increase quant tolerance slightly (for small Qwen2 models esp.)

2024-06-13 20:44:51 +02:00

tokenize.py

Add machine-parseable output to convert script

2024-05-20 01:49:34 +02:00