@@ -515,12 +515,11 @@ jobs:
515515 python3 torchchat.py generate --checkpoint-path ${MODEL_PATH} --temperature 0 --pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
516516
517517 echo "******************************************"
518- echo "*** can 't test --quantize torchchat/quant_config/mobile.json ***"
519- echo "*** testing --quantize torchchat/quant_config/mobile-32.json ***"
518+ echo "*** [TEST DISABLED] Can 't test --quantize torchchat/quant_config/mobile.json ***"
519+ echo "*** Testing --quantize torchchat/quant_config/mobile-32.json instead ***"
520520 echo "******************************************"
521- python torchchat.py export --quantize torchchat/quant_config/mobile-32.json --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
522- python3 torchchat.py generate --checkpoint-path ${MODEL_PATH} --temperature 0 --pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
523-
521+ # python torchchat.py export --quantize torchchat/quant_config/mobile-32.json --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
522+ # python3 torchchat.py generate --checkpoint-path ${MODEL_PATH} --temperature 0 --pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
524523
525524 echo "******************************************"
526525 echo "******* Emb: channel-wise quantized ******"
@@ -537,13 +536,13 @@ jobs:
537536 echo "******************************************"
538537 echo "**** Emb 4bit: channel-wise quantized ****"
539538 echo "******************************************"
540- python torchchat.py export --quant '{"embedding" : {"bitwidth": 8 , "groupsize": 0}}' --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
539+ python torchchat.py export --quant '{"embedding" : {"bitwidth": 4 , "groupsize": 0}}' --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
541540 python3 torchchat.py generate --checkpoint-path ${MODEL_PATH} --temperature 0 --pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
542541
543542 echo "******************************************"
544543 echo "****** Emb 4bit: group-wise quantized ****"
545544 echo "******************************************"
546- python torchchat.py export --quant '{"embedding" : {"bitwidth": 8 , "groupsize": 8}}' --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
545+ python torchchat.py export --quant '{"embedding" : {"bitwidth": 4 , "groupsize": 8}}' --checkpoint-path ${MODEL_PATH} --output-pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
547546 python3 torchchat.py generate --checkpoint-path ${MODEL_PATH} --temperature 0 --pte-path ${MODEL_DIR}/${MODEL_NAME}.pte
548547
549548 echo "******************************************"
0 commit comments