Eupham

Sorry I'm trying to figure out where we get trainer.mamba_trainer from.

Is there any chance of a notebook showing how to train with this? I'm doing something wrong in my attempts. `import os import torch from datasets import load_dataset, load_from_disk from...

Nevermind. This works for me. Adapted from [here](https://huggingface.co/Q-bert/Mamba-1B) `import torch from transformers import AutoTokenizer, TrainingArguments, Trainer from datasets import load_dataset, load_metric import numpy as np from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel model_name...

I'm getting the same problem. I went straight from pip install mamba-ssm and in generate I've added min_p as an argument. I'm getting the same error. This was in a...

It works now. Thanks for the fix.

Can you explain the use case here. Would this be like if the model is handling topic a, we're using and updating state a for each inference?

Just to be sure this is for a different use case than using cg=True for generate? Like in generate which is defined by DecodingCGCache and capture_graph in generation https://github.com/state-spaces/mamba/blob/main/mamba_ssm/utils/generation.py I'm...