Reinforcement Learning
Transformers
Safetensors
English
llama
text-generation
nlp
agent
text-generation-inference
Instructions to use xwm/SciWorld-MPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xwm/SciWorld-MPO with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("xwm/SciWorld-MPO") model = AutoModelForCausalLM.from_pretrained("xwm/SciWorld-MPO") - Notebooks
- Google Colab
- Kaggle
Fix pipeline tag, add links, improve model card
#1
by nielsr HF Staff - opened
This PR updates the model card with key information:
- Sets the pipeline tag to
reinforcement-learning. - Links to the paper and the associated code repository.
- Adds the base model and evaluation metrics to the metadata.
- Adds dataset information to the metadata.
xwm changed pull request status to merged