Mohammed Jabir

``` TypeError Traceback (most recent call last) [](https://localhost:8080/#) in () 10 11 # Load VQGAN ---> 12 vqgan = VQModel.from_pretrained(VQGAN_REPO, revision=VQGAN_COMMIT_ID) 13 14 # Load CLIP 1 frames [/usr/local/lib/python3.7/dist-packages/vqgan_jax/modeling_flax_vqgan.py](https://localhost:8080/#) in...

@fedshyvana I believe this is how biogpt is trained on fairseq . For more information , you check into official repo of BioGpt.

@fedshyvana bos_token_id , eos_token_id is added to vocabulary as we always do for every tokenizer.But during building inputs with special tokens, we are only considering eos_token_id . Although we are...

@NielsRogge @sgugger can you please look into it ?

sure, Let me work on it

@kurchi1205 Am working on it . The problem is that biogpt doesnt have fast tokenizer . Currenlty am in a testing phase

Hi @GuillemGSubies. If the issue is still open, i would like to contribute it. Thanks

@GuillemGSubies currently I don't have any idea about the issue. But let me try it, so I can get a clear picture

@ttssp I believe by default save_steps=100, and you are trying to run fine-tuning only for 2 steps. Try reducing save_steps to 1 or 2.