picoGPT

picoGPT copied to clipboard

Daniyal branch

1

Added temperature

M-Daniyal-123

is it better to change return x @ wte.T # [n_seq, n_embd] -> [n_seq, n_vocab] by x[-1] @ wte.T ? then we can use next_id = np.argmax(logits)

Sandy4321

do you have video to this code in addition to your blog https://jaykmody.com/blog/gpt-from-scratch/

Sandy4321

can it be run on windows ? meaning do I need on windows this line tensorflow-macos==2.11.0; sys_platform == 'darwin' and platform_machine == 'arm64' in https://github.com/jaymody/picoGPT/blob/main/requirements.txt

Sandy4321

``` C:\Users\JohanIsaksson\source\repos\picoGPT>python gpt2.py "Alan Turing theorized that computers would one day become" Traceback (most recent call last): File "C:\Users\JohanIsaksson\source\repos\picoGPT\gpt2.py", line 119, in import fire ModuleNotFoundError: No module named 'fire' C:\Users\JohanIsaksson\source\repos\picoGPT>pip...

izaxon