This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FROM python:3.10-bookworm | |
# Install system dependencies required for gmpy2 | |
RUN apt-get update && apt-get install -y \ | |
libmpfr-dev \ | |
libmpc-dev \ | |
libgmp-dev \ | |
&& rm -rf /var/lib/apt/lists/* | |
COPY agent-python-requirements.txt . |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from typing import Dict, Any | |
from inspect_ai import Task, task, Epochs | |
from inspect_ai.dataset import Sample, hf_dataset | |
from inspect_ai.scorer import scorer, Score, Target, CORRECT, INCORRECT, accuracy, stderr | |
from inspect_ai.solver import generate, prompt_template, TaskState | |
from bench.model import default_grader_model | |
SOLUTION_TEMPLATE = """Please solve this AIME problem step by step. The answer is an integer ranging from |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import random | |
from string import ascii_uppercase | |
from typing import Dict, Any | |
from inspect_ai import task, Task | |
from inspect_ai.dataset import Sample | |
from inspect_ai.dataset._sources.hf import hf_dataset | |
import inspect_ai.solver | |
import inspect_ai.scorer |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from typing import Optional, List | |
from inspect_ai._eval.registry import task | |
from inspect_ai._eval.task import Task | |
from inspect_ai.dataset._sources.hf import hf_dataset | |
from bench.model import DEFAULT_GRADER_MODEL | |
from bench.task.hendrycks_math.dataset import filter_dataset, record_to_sample | |
from bench.task.hendrycks_math.scorer import ( | |
normalized_string_match, |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Jekyll plugin to replace Markdown image syntax with {% picture %} tag for crafting responsive images | |
# Adapted from https://gist.github.com/mmistakes/77c68fbb07731a456805a7b473f47841 | |
# Use as a gem: https://github.com/tadamcz/jekyll-markdown-responsive-image | |
Jekyll::Hooks.register [:pages, :documents], :pre_render do |post, payload| | |
file_ext = post.extname.tr('.', '') | |
# This regex will match all of the following correctly: | |
# |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
git diff origin/master --name-only --diff-filter=ACMRTUXB | grep "\.rb$" | tr "\n" " " | xargs bundle exec rubocop -A --force-exclusion |