Instructions to use google/madlad400-7b-mt-bt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/madlad400-7b-mt-bt 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="google/madlad400-7b-mt-bt")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/madlad400-7b-mt-bt") model = AutoModelForSeq2SeqLM.from_pretrained("google/madlad400-7b-mt-bt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from google/madlad400-7b-mt-bt: direct link, hf CLI and curl.
- Browser
- Download file 16.6 MB
-
https://huggingface.co/google/madlad400-7b-mt-bt/resolve/main/tokenizer.json
- Command line
-
hf download hf://google/madlad400-7b-mt-bt/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/google/madlad400-7b-mt-bt/resolve/main/tokenizer.json
16.6 MB
- Xet hash:
- 828d0ef75e270ab2aeb2358cba3a69db8b24ab9c479fe2847c89b36163f76aa9
- Size of remote file:
- 16.6 MB
- SHA256:
- a2799ccc696b752ba00c34f58726bfe253a04921ceb6cfc620400f560474790b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.