Text Generation
PEFT
Safetensors
lora
fine-tuning
multi-task
continual-learning
natural-language-understanding
causal-lm
Instructions to use juzhengz/LoRI-S_nlu_llama3_rank_64 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use juzhengz/LoRI-S_nlu_llama3_rank_64 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "juzhengz/LoRI-S_nlu_llama3_rank_64") - Notebooks
- Google Colab
- Kaggle
Enhance model card for LoRI-S_nlu_llama3_rank_64 with comprehensive details
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for tomg-group-umd/LoRI-S_nlu_llama3_rank_64 by incorporating detailed information from the paper 'LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation' and its associated GitHub repository.
Key updates include:
- Adding the paper's abstract and key highlights to provide a quick overview.
- Specifying the license as Apache 2.0 in both metadata and content.
- Adding relevant tags to the metadata for improved discoverability on the Hugging Face Hub.
- Populating sections like 'Model Details', 'Uses', 'Bias, Risks, and Limitations', 'How to Get Started with the Model', 'Training Details', and 'Evaluation'.
- Providing a runnable Python code example for model inference.
- Including explicit links to the GitHub repository and the project's Hugging Face collection.
- Adding the full BibTeX citation.
These changes make the model card much more informative and user-friendly, allowing researchers and practitioners to understand and use the model effectively.
juzhengz changed pull request status to merged