Instructions to use issai/tilmash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use issai/tilmash with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="issai/tilmash")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("issai/tilmash") model = AutoModelForSeq2SeqLM.from_pretrained("issai/tilmash") - Notebooks
- Google Colab
- Kaggle
How many times you spend for training?
#3
by blackagargrom - opened
How many times you spend for training? And which GPU version was used? RTX3060 maybe?
How many times you spend for training? And which GPU version was used? RTX3060 maybe?
Hello. For this model, we spend about 3 days for 3 epochs on 8 A100 GPUs. We also trained it on V100 and we spent about 4-5 days for the same number of epochs.
How many times you spend for training? And which GPU version was used? RTX3060 maybe?
We haven't trained it on RTX3060, I think it is possible but it will take a lot of time for a big dataset such as KazParc.