datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
REASONING_evalchemy_64_sharded_gpt-4o-mini
Dataset card for REASONING_evalchemy_64_sharded_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Generate an executable Python function generated from the given prompt. Return the function body without invoking it at the final solution.You are given a 0-indexed array nums of n integers and an integer target.\nYou are initially positioned at index 0. In one step, you can… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_64_sharded_gpt-4o-mini.reward-bench-gpt-4o-mini-yes-noREASONING_evalchemy_sharded_gpt-4o-mini
Dataset card for REASONING_evalchemy_sharded_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Generate an executable Python function generated from the given prompt. The function should take stdin as input and print the output. Simply call the function after the definition.There are three cards with letters $\\texttt{a}$, $\\texttt{b}$, $\\texttt{c}$ placed in a row in some… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_sharded_gpt-4o-mini.REASONING_evalchemy_8_sharded_gpt-4o-mini
Dataset card for REASONING_evalchemy_8_sharded_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Problem: What is the degree measure of the acute angle formed by lines with slopes $2$ and $\\frac{1}{3}$?\nMark your solution with \\boxed\nAnswer:",
"role": "user"
}
],
"gen_kwargs": {
"do_sample": false,
"max_new_tokens": 32768… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_8_sharded_gpt-4o-mini.REASONING_evalchemy_32_sharded_gpt-4o-mini
Dataset card for REASONING_evalchemy_32_sharded_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Problem: How many of the same digits are found in the base 7 and base 8 representations of $629_{10}$? For example, $121_{3}$ and $413_{5}$ would have one digit in common.\nMark your solution with \\boxed\nAnswer:",
"role": "user"
}
],
"gen_kwargs": {… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_32_sharded_gpt-4o-mini.REASONING_evalchemy_32_shards_gpt-4o-mini
Dataset card for REASONING_evalchemy_32_shards_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Problem: Find the number of quadratic equations of the form $x^2 + ax + b = 0,$ such that whenever $c$ is a root of the equation, $c^2 - 2$ is also a root of the equation.\nMark your solution with \\boxed\nAnswer:",
"role": "user"
}
],
"gen_kwargs": {… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_32_shards_gpt-4o-mini.GPQADiamond_evalchemy_gpt-4o-mini
mlfoundations-dev/GPQADiamond_evalchemy_gpt-4o-mini
Precomputed model outputs for evaluation.
Evaluation Results
AIME25
Average Accuracy: 0.00% ± 0.00%
Number of Runs: 5
Run
Accuracy
Questions Solved
Total Questions
1
0.00%
0
30
2
0.00%
0
30
3
0.00%
0
30
4
0.00%
0
30
5
0.00%
0
30
gpt_4o_mini_classifications_multi_humanapollo_english_guidelines_translated_to_dutch_with_gpt4omini
Data description
Translation of the English medical guidelines that are part of the Apollo corpus, using the LLM GPT 4o mini
Acknowledgement
The work received funding from the European Union's Horizon Europe research
and innovation programme under Grant Agreement No. 101057849 (DataTools4Heart project).
For more information on the background, see Datatools4Heart Huggingface/Website/Git
PersonaSignal-LeakageCheck-Agency-Expectation-gpt-4o-miniPersonaSignal-LeakageCheck-Programming-Expertise-gpt-4o-miniPersonaSignal-LeakageCheck-Locale-And-Time-Zone-gpt-4o-miniPersonaSignal-LeakageCheck-Verification-Orientation-gpt-4o-miniPersonaSignal-LeakageCheck-Communication-Formality-gpt-4o-miniairoboros_stage_2_gpt-4o-miniPersonaSignal-LeakageCheck-Social-Scope-gpt-4o-miniPersonaSignal-LeakageCheck-Learning-Goal-gpt-4o-miniPersonaSignal-LeakageCheck-Feedback-Style-gpt-4o-miniPersonaSignal-LeakageCheck-Planning-Horizon-gpt-4o-miniPersonaSignal-LeakageCheck-Exploration-Tendency-gpt-4o-miniREASONING_evalchemy_16_sharded_gpt-4o-mini
Dataset card for REASONING_evalchemy_16_sharded_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Problem: If $\\frac{\\sqrt{2x}}{\\sqrt{3x-1}}=\\frac32$, solve for $x$. Express your answer in simplest fractional form.\nMark your solution with \\boxed\nAnswer:",
"role": "user"
}
],
"gen_kwargs": {
"do_sample": false… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_16_sharded_gpt-4o-mini.PersonaSignal-All-Leakage_Check-gpt-4o-miniairoboros_stage_2_gpt-4o-mini_no_filterepfl_english_guidelines_translated_to_dutch_with_gpt4omini
Dataset Card for Epfl English Guidelines Translated To Dutch With Gpt4Omini
This dataset was created by the EPFL, and can found in it original form here
The source language: English
The original data source: Original Data Source
Data description
Translation of the English medical guidelines that are part of the Meditron corpus, using the LLM GPT 4o mini
Acknowledgement
This is part of the DT4H project with attribution [Cite the paper].
Doi and… See the full description on the dataset page: https://huggingface.co/datasets/UMCU/epfl_english_guidelines_translated_to_dutch_with_gpt4omini.REASONING_evalchemy_gpt-4o-mini
Dataset card for REASONING_evalchemy_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Generate an executable Python function generated from the given prompt. The function should take stdin as input and print the output. Simply call the function after the definition.There are three cards with letters $\\texttt{a}$, $\\texttt{b}$, $\\texttt{c}$ placed in a row in some order.… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_gpt-4o-mini.REASONING_evalchemy_4shards_gpt-4o-mini
Dataset card for REASONING_evalchemy_4shards_gpt-4o-mini
This dataset was made with Curator.
Dataset details
A sample from the dataset:
{
"context": [
{
"content": "Problem: A list of positive integers has the following properties: $\\bullet$ The sum of the items in the list is $30$ . $\\bullet$ The unique mode of the list is $9$ . $\\bullet$ The median of the list is a positive integer that does not appear in the list itself. Find the… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/REASONING_evalchemy_4shards_gpt-4o-mini.camel_math_gpt-4o-mini_1xgpt-4o-mini_Banking_Exam_MCQbigcodebench-complete_qwen7b_gpt-4o-mini_att_iter0_att10_sol5camel_math_gpt-4o-mini