Instructions to use haiFrHust/VNJPTranslate_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use haiFrHust/VNJPTranslate_base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" 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("question-answering", model="haiFrHust/VNJPTranslate_base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("haiFrHust/VNJPTranslate_base") model = AutoModelForCausalLM.from_pretrained("haiFrHust/VNJPTranslate_base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from haiFrHust/VNJPTranslate_base: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/haiFrHust/VNJPTranslate_base/resolve/main/tokenizer.json
- Command line
-
hf download hf://haiFrHust/VNJPTranslate_base/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/haiFrHust/VNJPTranslate_base/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 174fe6645a699058e60a1dc1983178c871dfdad9a74b50de09d7cc84c01a3409
- Size of remote file:
- 11.4 MB
- SHA256:
- f57c08ad24777342a4fe089b821fcc1c19e7dae2a66fd172ceea62a7fd9ed805
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.