VatsaDev

Whats your environment? Do you have the config file? Did you add anything to the CLI? Is every command formatted right?

just set them in the train config with --block_size, vocab size is tokenizer size, depends on BPE or char, not a you setting > "vocab_size" needs to be larger than...

That Chatgpt response has legit ripped the words from https://saturncloud.io/blog/how-to-clear-gpu-memory-after-pytorch-model-training-without-restarting-kernel/, but you should make this a PR, and the del keyword doesnt need gc, should clear mem immediatly

The best I could do was generate, then string partition, This works fine for short inference, but is terrible for long ones

If you mean gpt-3 level, You're several billion parameters short. If you mean ChatGPT, then you need RLHF and finetuning on conversational data. The best I could get was using...

I finetuned the gpt2 model from the walk through on the readme, and have forked and ran hundreds of times, definitely works

@vladimirlitvinyuk You are talking about a model with anywhere between 124 million to 1.5 billion parameters. It doesn't make duplicates very often, unless you give it some very narrow input....

@Yusuf-YENICERI ``` Message: Support has been terrible for 2 weeks... Sentiment: Negative ### Message: I love your API, it is simple and so fast! Sentiment: Positive ### Message: GPT-J has...

You don't need a GPU on your machine to use NanoGPT, an environment like google colab can easily support up till gpt2-medium, and maybe more, depending on how you change...

@nashcaps2255 You are not under a false impression, You Probably can do the above task, but it depends a lot on your model, hyperparameters, and dataset size. I have a...