--- language: - en datasets: - The Pile - super_glue tags: - pytorch - causal-lm - 8bit inference: false --- side project, not final working good product see [this repo](https://huggingface.co/crumb/gpt-j-6b-shakespeare) for more information, finetuned with [8-bit Adam](https://arxiv.org/abs/2110.02861) on custom transformed super glue tasks, transformed somewhat like the [T0 paper](https://arxiv.org/abs/2110.08207) ```python from IPython import display !pip install transformers==4.14.1 -q !pip install bitsandbytes-cuda111==0.26.0 -q !pip install git+https://github.com/aicrumb/transformers-8bit -q import transformers_8bit model, tokenizer, config = transformers_8bit.gptj("crumb/gpt-j-6b-finetune-super-glue", device='cuda') prompt = tokenizer(" If birds are in group B, and snakes are in group A, what group are pythons in? ", return_tensors='pt') prompt = {key: value.to('cuda') for key, value in prompt.items()} length = len(prompt['input_ids'][0]) out = model.generate(**prompt, min_length=length+2, max_length=length+2, do_sample=False, pad_token_id=tokenizer.eos_token_id) print(tokenizer.decode(out[0])) """output If birds are in group B, and snakes are in group A, what group are pythons in? Group A """ ```