Ensheng Shi (石恩升)

Expected combineable dataset

1

I download tensorflow from https://polybox.ethz.ch/index.php/s/ojd0RPFOtUTPPRr and put tensorflow/ir_0 in data/. When i run `python train_inst2vec.py`, there is a error : "Expected combineable dataset" I know the except is from https://github.com/spcl/ncc/blob/master/inst2vec/inst2vec_embedding.py#L56....

[run llama-13b] NameError: name 'cuda_setup' is not defined. Did you mean: 'CUDASetup'?

2

run ```python server.py --share --listen --chat --model llama-7b```. Everything is okay.  However, when run ```` python server.py --share --listen --chat --model llama-13b ```, It would report an error: ```...

Take too much time to load the model

2

It takes too much time to load the model . For example, setting batch size =1, It will take about 252.89 and 880s to load llama-13b and llama-30b, respectively. Are...

refer to https://github.com/randaller/llama-chat/issues/7

AttributeError: 'NoneType' object has no attribute 'to'

1

code `python generate.py ` error ``` ===================================BUG REPORT=================================== Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues ================================================================================ /home/t-enshengshi/anaconda3/envs/alpaca-lora/lib/python3.9/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: /home/t-enshengshi/anaconda3/envs/alpaca-lora did not contain libcudart.so as...

I run the program on 4*V100. When setting group_by_lenth=True, the training loss often decreases and coverages.  When setting group_by_lenth=False, the training loss often becomes suddenly bigger and then it...

Why add the following code snippet since it would bring some errors?

20

Why add the following code snippet in this [commit](https://github.com/tloen/alpaca-lora/commit/5fa807d106fdce88bd9635eac9fee1a7be9465ae#diff-a5ff12394959301eb25d323d44fc987a79336e66a44eb3e4def7ae3515f35430) since it would bring some errors? https://github.com/tloen/alpaca-lora/blob/main/finetune.py#L256-L261 ``` old_state_dict = model.state_dict model.state_dict = ( lambda self, *_, **__: get_peft_model_state_dict( self, old_state_dict()...

What is the maximum token limit of llama?

9

What is the maximum token limit of llama? Is it 1024, 2048, 4096, or longer? for example, GPT-4 has a maximum token limit of 32,000 (equivalent to 25,000 words)

How to get PDG in commandline

1

I find about code about /ProgramDependenceGraph https://github.com/soot-oss/soot/blob/4a04145d1a4d2713ef2733e33abd5ba77b2fd848/src/main/java/soot/toolkits/graph/pdg/ProgramDependenceGraph.java , however I don't know how to get PDG in command line using soot