zhihan1996
/

DNABERT-2-117M

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (6)

TypeError: dot() got an unexpected keyword argument 'trans_b'

#36 opened 3 days ago by

Where to find Pretraining Code?

#35 opened 17 days ago by

add autoconfig

#34 opened 22 days ago by

CUDA: OutOfMemoryError

#33 opened about 2 months ago by

Make compatible with recent versions of triton

#32 opened 4 months ago by

Adding `safetensors` variant of this model

#31 opened 5 months ago by

Example Notebook

#29 opened 7 months ago by

Encoding for long contexts

#28 opened 7 months ago by

Fix AutoModel not loading model correctly due to config_class inconsistency

#26 opened 10 months ago by

Update bert_layers.py

#25 opened 10 months ago by

A modified DNABERT2 that returns the attention too

#24 opened 10 months ago by

Triton version

#23 opened 11 months ago by

how do I output the attention scores from the last layer of the encoder?

#22 opened 11 months ago by

Tokenization of more than 2 sequences

#21 opened 12 months ago by

Impact of Padding on DNABERT Model Performance

#20 opened about 1 year ago by

Setting DNABERT-2 revision

#19 opened about 1 year ago by

TypeError: forward() got an unexpected keyword argument 'attention_mask'

#18 opened about 1 year ago by

Adding `safetensors` variant of this model

#17 opened about 1 year ago by

Assertion Error / Implementation Error

#16 opened about 1 year ago by

Extract attention from model

#15 opened about 1 year ago by

error on inference using DNABERT2 - can you please share the environment you used for running it?

#12 opened over 1 year ago by

Adding `safetensors` variant of this model

#11 opened over 1 year ago by

Is the datasets for foundational model pre-training publicly accessible?

#10 opened over 1 year ago by

Expecting bi-modal disstribution of probabilities

#9 opened over 1 year ago by

christianclough

Inference fails with output_all_encoded_layers=True.

#8 opened over 1 year ago by

Adding `safetensors` variant of this model

#7 opened over 1 year ago by

The model class you are passing has a `config_class` attribute that is not consistent with the config class you passed

#6 opened over 1 year ago by

About the output of tokenizer and the model

#4 opened over 1 year ago by

Despite multiple trials and examining the model configuration, it seems that the model hosted on Hugging Face (`huggingface.co`) cannot handle sequences that exceed a length of 512 tokens.

#3 opened over 1 year ago by

Issue in Code, at 114:24: def _fwd_kernel(..)

#1 opened over 1 year ago by