minGPT
minGPT copied to clipboard
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Cs674
https://github.com/karpathy/minGPT/blob/37baab71b9abea1b76ab957409a1cc2fbfba8a26/projects/adder/adder.py#L118 https://github.com/karpathy/minGPT/blob/37baab71b9abea1b76ab957409a1cc2fbfba8a26/projects/adder/adder.py#L89
Adds a three-line method which uses namedtuple to create frozen configs if one wants to avoid footguns. Checks off the 'todo' item in config. Elements of the config are still...
For example, chinese or japanese?
How can I run a trained model? Include/ Projects/add/model. pt. Test_ Hugging face_ Import. py directly runs this test program and reports File ".\minGPT\master\mingpt model. py", line 202, in from_...
It seems that the output of this block is simply reshaped from multiple heads. From the original "Attention is all you need" paper, it seems that there is another linear...
Generator repl enables interaction with adder model checkpoint.
Issue:Renaming transformer.h into transformer.l #94 Url: https://github.com/karpathy/minGPT/issues/94 Fix: Renaming transformer.h into transformer.l in line 270 of model.py file and added comments
In model.py, the implementation of layer norm is : self.ln_1 = nn.LayerNorm(config.n_embd) If batch_size = 64, block_size = 6, embedding_size = 48, then the shape of input is [64, 6,...