krisliu
/

Quantization_Assistant_LLaMA2_Accessory

Model card Files Files and versions Community

krisliu commited on Aug 21, 2023

Commit

c3dc7ae

·

1 Parent(s): 3ead474

fix bug

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ For the checkpoints located in the `finetune/mm/` directory, use the following c
 torchrun --nproc-per-node=1 demos/single_turn_mm.py \
 --llama_config <path-to-params.json> \
 --tokenizer_path <path-to-tokenizer.model> \
---pretrained_path <stage1-of-lamaQformerv2_13b> <this-repo>/finetune/mm/alpacaLlava_llamaQformerv2Peft_QF_13B/ \
 --quant \
 --llama_type llama_qformerv2_peft

 torchrun --nproc-per-node=1 demos/single_turn_mm.py \
 --llama_config <path-to-params.json> \
 --tokenizer_path <path-to-tokenizer.model> \
+--pretrained_path <stage1-of-lamaQformerv2_13b> <this-repo>/finetune/mm/alpacaLlava_llamaQformerv2Peft_QF_13B/epoch2 \
 --quant \
 --llama_type llama_qformerv2_peft