Instructions to use allenai/Llama-3.1-70B-Instruct-RM-RB2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use allenai/Llama-3.1-70B-Instruct-RM-RB2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="allenai/Llama-3.1-70B-Instruct-RM-RB2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("allenai/Llama-3.1-70B-Instruct-RM-RB2") model = AutoModelForSequenceClassification.from_pretrained("allenai/Llama-3.1-70B-Instruct-RM-RB2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model-00003-of-00029.bin from allenai/Llama-3.1-70B-Instruct-RM-RB2: direct link, hf CLI and curl.
- Browser
- Download file 5 GB
-
https://huggingface.co/allenai/Llama-3.1-70B-Instruct-RM-RB2/resolve/refs%2Fpr%2F2/pytorch_model-00003-of-00029.bin
- Command line
-
hf download hf://allenai/Llama-3.1-70B-Instruct-RM-RB2@refs/pr/2/pytorch_model-00003-of-00029.bin
-
curl -L -o pytorch_model-00003-of-00029.bin https://huggingface.co/allenai/Llama-3.1-70B-Instruct-RM-RB2/resolve/refs%2Fpr%2F2/pytorch_model-00003-of-00029.bin
5 GB
- Xet hash:
- ab1bcd03add408dfdc487b5111d5f5dcde7c78206429d2b456957c77b67cbd04
- Size of remote file:
- 5 GB
- SHA256:
- fd50ced21a93cf12781014533f91816dbcc63a750148b6a1073031517a43602b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.