Giters
bigscience-workshop
/
interpretability-ideas
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1
Watchers:
24
Issues:
10
Forks:
1
bigscience-workshop/interpretability-ideas Issues
Implement the paper: https://arxiv.org/abs/nlin/0409024
Updated
2 years ago
Research: probe for recursion in networks
Updated
2 years ago
Allow to probe an arbitrary model's checkpoints with the off-the-shelf probes
Updated
2 years ago
Provide the unified Interpretability API for both Huggingface and NON-Huggingface models
Updated
2 years ago
Provide the unified interpretability cookbooks
Updated
2 years ago
Implement and perform the interpretability analysis of the BigScience models
Updated
2 years ago
Imlement tests for abstract structures such as in Curcuits thread
Updated
2 years ago
Integrate existing tools: Captum, LIT, AllenNLP Interpret, NeuroX into the HF pipeline
Updated
2 years ago
Implement the unified attention interpretation API for similar models
Updated
2 years ago
Implement the unified activations interpretation API for similar models
Updated
2 years ago