Henry comments

Repositories
Issues
Comments

Results 3 comments of


                                            Henry

Fixing inconsistency between generated entropy value type and the expected HDWallet.entropy value type

> Hi @henryyuanheng-wang , > > I have a question regarding `test_payment_address_12_reward2()` test case. For this test, I see that you are explicitly specifying `private=False` for the last two derivation...

Error while loading finetuned model for inferencing.

I think with the default `finetune_lora.sh` script, `bf16` field is set to True, meaning the training is done in 16 bits by default. When loading the models for inference, setting...

RuntimeError : Error(s) in loading state_dict for LlavaLlamaForCausalLM

把load_4bit设置成False I think with the default `finetune_lora.sh` script, `bf16` field is set to True, meaning the training is done in 16 bits by default. When loading the models for inference,...