PyTorch RuntimeError: No operator found for memory_efficient_attention_forward with torch.float16 inputs on CPU
I am working with a PyTorch model (AutoModelForCausalLM) using the transformers library and encountering a RuntimeError related to tensor types and operator support. Here’s a simplified version of my code:
dimensions od mask and tensor stays different
im working on a model that learns chess through ddqn reinforcement learning , in short, in this specific snippet of the code:
Transposing and concatenating tensors in PyTorch
I have two tensors in PyTorch: