Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: mit

Fine-tuned GPT-2 (small) — Boolean Logic Task

GPT-2 small fine-tuned on the Boolean-logic task from Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction (arXiv:2605.02234).

Used by the logic_task experiments (DAS layer/position L5/P78 and L7/P77) and by the supplementary PCA-clustering baseline notebook (notebooks/pca_baselines.ipynb) in the project repository.

Architecture and tokenizer are standard gpt2; only the weights differ.

python

from transformers import GPT2LMHeadModel, GPT2Tokenizer
model = GPT2LMHeadModel.from_pretrained("PaulineLi/bucketing-good-apples-gpt2-logic")
tok = GPT2Tokenizer.from_pretrained("PaulineLi/bucketing-good-apples-gpt2-logic")

Model provider

PaulineLi

Model tree

Base

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today