Hugging Face's logo

flax-community
/
bengali-t5-base

Text2Text Generation
Transformers
PyTorch
JAX
TensorBoard
Safetensors
mt5
Inference Endpoints
Model card Files Metrics Community
1
sbmaruf commited on
Commit
681e8b4
•
1 Parent(s): d036995

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -27,7 +27,8 @@ The model is trained on around ~11B tokens (64 size batch, 512 tokens, 350k step
27
  ```
28
 
29
  The model is trained on `de-noising` objectives followed by the script [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run_t5_mlm_flax.py) and [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run.sh). Currently This model doesn't have any generation capability. If you want this model to have generation capability, please do a finetuning on `prefix-LM` objective mentioned in the [paper](https://arxiv.org/abs/1910.10683).
30
- Please note that we haven't finetuned the model in any downstream task. If you are finetuning the model in any downstream task, please let us know about it. Shoot us an email (sbmaruf at gmail dot com)
 
31
 
32
  ## Proposal
33
  - [Project Proposal](https://discuss.huggingface.co/t/pretrain-t5-from-scratch-in-bengali/7121)
 
27
  ```
28
 
29
  The model is trained on `de-noising` objectives followed by the script [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run_t5_mlm_flax.py) and [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run.sh). Currently This model doesn't have any generation capability. If you want this model to have generation capability, please do a finetuning on `prefix-LM` objective mentioned in the [paper](https://arxiv.org/abs/1910.10683).
30
+
31
+ Please note that we haven't finetuned the model in any downstream task.
32
 
33
  ## Proposal
34
  - [Project Proposal](https://discuss.huggingface.co/t/pretrain-t5-from-scratch-in-bengali/7121)