LLM Train and Inference vs Right Padding and Left Padding – LLM Tutorial
Padding method will affect the performance of LLM. There are two padding method: left and right padding.
Understand tokenizer add_special_tokens with Examples in LLM – LLM Tutorial
As to a tokenizer instance, it contains add_special_tokens parameter. In this tutorial, we will introduce what it mean.
Understand padding_side with Examples in LLM – LLM Tutorial
Most of LLMs are decoder-only architectures, which means they are not trained to continue from pad tokens. This strategy may cause wrong outputs when batch inference.
Understand load_in_8bit in AutoModelForCausalLM.from_pretrained() – LLM Tutorial
In this tutorial, we will introduce load_in_8bit parameter in AutoModelForCausalLM.from_pretrained()
An Simple Guide to Fix Torch NAN Error – PyTorch Tutorial
In this tutorial, we will tell you a simple way to find and solve the nan error when training a torch model.
Understand Transformers tokenizer.encode() with Examples – LLM Tutorial
tokenizer is widely used in huggingface, especially for tokenizer.encode(). In this tutorial, we will use llama2 tokenizer to show you how to use it.
PyTorch Save Models with Limited Model Number – PyTorch Tutorial
In this tutorial, we will introduce you how to limit the count of models when we are training a pytorch model.
Fix impala fs.get_code() SyntaxError: invalid syntax – Python Tutorial
In this tutorial, we will use an example to show you how to fix impala fs.get_code() SyntaxError: invalid syntax error.
Python Detect a WAV File is Compressed or not – Python Tutorial
In this tutorial, we will use an example to introduce you how to detect a wav file is compressed or not.
Compare Two Torch Tensors have the Same Shape or not – PyTorch Tutorial
In this tutorial, we will use an example to show you how to compare two torch tensors whether have the same shape or not.