metadata
license: apache-2.0
metrics:
- accuracy
base_model:
- meta-llama/Llama-3.1-8B-Instruct
Model Card for Llama8b-NNetNav-WA
LLama8b-NNetNav-WA is a LLama-3.1-8B model that is instruct-tuned with NNetNav data collected via unsupervised exploration on WebArena websites, with a larger LLama-3.1-70B model.
Most details about this model along with details can be found in our paper: NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild.
Table of Contents
- Model Card for Llama8b-NNetNav-WA
- Table of Contents
- Model Details
- Uses
- Bias, Risks, and Limitations
- Training Details
- Environmental Impact
- Technical Specifications [optional]
- Citation
- Model Card Authors [optional]
- Model Card Contact
- How to Get Started with the Model
Model Details
Model Description
Uses
Bias, Risks, and Limitations
How to Get Started with the Model
Training Details
Training Data
This model was trained on the NNetnav-WA corpus.
Training Procedure
This model was trained for 2 epochs (roughly 4k gradient steps) with a batch size of 128, and a maximum sequence length of 20000.
Environmental Impact
- Hardware Type: 4 H100 GPUs (80G)
- Hours used: Roughly 2 days.
- Cloud Provider: Stanford compute.
- Compute Region: Stanford energy grid.
Model Architecture and Objective
Compute Infrastructure
This model was trained on a slurm cluster.
Hardware
This model was trained on 4 H100s.
Software
This model was fine-tuned with Open-Instruct
Citation
BibTeX:
Model Card Authors [optional]
Shikhar Murty