datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_bestdive__SmolLM3-3B-SFT-Free-Course
Smol course SFT evaluation - Kay Zheng
Actual full GSM8K test evaluation of bestdive/SmolLM3-3B-SFT-Free-Course, adapter revision 0484e028b494d605a267050a949c9266edadd16b, merged with pinned SmolLM3-3B-Base before evaluation.
Full 1319 test examples, zero-shot, original extractive_match: 0.4086429112964367 (stderr 0.013540639733342422).
Free Google Colab T4, no paid HF Jobs; cost 0.
lighteval 0.11.0, vLLM 0.10.1.1, Transformers 4.57.1, Python 3.12.
Dataset-address correction… See the full description on the dataset page: https://huggingface.co/datasets/bestdive/details_bestdive__SmolLM3-3B-SFT-Free-Course.tis-subset-datasets-SmolLM3-3B-Basedetails_pmakiela__SmolLM3-3B-dpo-v0_1_private
Dataset Card for Evaluation run of pmakiela/SmolLM3-3B-dpo-v0_1
Dataset automatically created during the evaluation run of model pmakiela/SmolLM3-3B-dpo-v0_1.
The dataset is composed of 4 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/pmakiela/details_pmakiela__SmolLM3-3B-dpo-v0_1_private.tis-dolci-subset-datasets-SmolLM3-3B-Basedetails_FrancescoArno94__SmolLM3-3B-math_private
Dataset Card for Evaluation run of FrancescoArno94/SmolLM3-3B-math
Dataset automatically created during the evaluation run of model FrancescoArno94/SmolLM3-3B-math.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.… See the full description on the dataset page: https://huggingface.co/datasets/FrancescoArno94/details_FrancescoArno94__SmolLM3-3B-math_private.MMLU-Pro_SmolLM3-3B_test
MMLU-Pro_SmolLM3-3B_test
tis-dolci-quantile-datasets-SmolLM3-3B-Basesmollm3-3b-base-blind-spots
SmolLM3-3B-Base Blind Spots Dataset
This dataset contains 10 test cases where I explored the failure modes of
SmolLM3-3B-Base,
a 3 billion parameter base language model released by HuggingFace in 2025.
The goal was to find diverse cases where the model makes clearly incorrect
or unexpected completions its "blind spots."
Model Tested
Model: HuggingFaceTB/SmolLM3-3B-Base
Parameters: 3B
Type: Base pretrained model
License: Apache 2.0
How I Loaded the Model
I… See the full description on the dataset page: https://huggingface.co/datasets/FatimaAfzal01/smollm3-3b-base-blind-spots.details_HuggingFaceTB__SmolLM3-3B_private
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM3-3B
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM3-3B.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/andregustavo/details_HuggingFaceTB__SmolLM3-3B_private.olmes-eval-smollm3-3b-base
olmes-eval-smollm3-3b-base
OLMES evaluation results for SmolLM3-3B base.
Provenance
This dataset was renamed on 2026-05-25 as part of the HCAI-Lab HF naming convention cleanup (PR 3). See docs/HCAI_LAB_NAMING_CONVENTION.md in the project repo for the convention.
Field
Value
Previous name
HCAI-Lab/data-attribution-smollm3-3b-base-evaluation
Renamed
2026-05-25
See docs/data_home/inventory.json for the full inventory including the old_names field on… See the full description on the dataset page: https://huggingface.co/datasets/HCAI-Lab-GT/olmes-eval-smollm3-3b-base.LEXam_SmolLM3-3B_testdetails-smollm3-3b-sft-finetuned-jobs-v2
Dataset Card for Evaluation run of marcelovidigal/smollm3-3b-sft-finetuned-jobs-v2
Dataset automatically created during the evaluation run of model marcelovidigal/smollm3-3b-sft-finetuned-jobs-v2.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/marcelovidigal/details-smollm3-3b-sft-finetuned-jobs-v2.details_Jake__SmolLM3-3B-Math-SFT_privatesmollm3-3b-blind-spots
smollm3-3b-blind-spots
A curated dataset of 12 diverse failure-mode examples collected by probing
HuggingFaceTB/SmolLM3-3B,
a 3-billion-parameter base language model released on July 8, 2025.
Each row contains the prompt fed to the model, the expected correct output,
and the model's actual greedy-decoded output.
Model
Field
Value
Model
HuggingFaceTB/SmolLM3-3B
Parameters
3B
Type
Base (pretrained only — no instruction tuning)
Released
July 8, 2025… See the full description on the dataset page: https://huggingface.co/datasets/dagmaros27/smollm3-3b-blind-spots.SmolLM3-3B-customerservice-evaldatatis-quantile-datasets-SmolLM3-3B-BaseSuperGPQA-SmolLM3-3BBlind_Spots_Dataset_SmolLM3-3B-Base
SmolLM3-3B-Base Blind Spots Dataset
Dataset Summary
This dataset documents 13 failure cases of the HuggingFaceTB/SmolLM3-3B-Base model, a 3-billion parameter base language model pretrained on 11.2 trillion tokens. Each row contains a text completion prompt, the expected correct output, the model's actual output, and the category. The dataset spans 13 distinct categories in which the SmolLM3-3B-Base model fails to work as expected.
Model Tested
Model:… See the full description on the dataset page: https://huggingface.co/datasets/Yanmife/Blind_Spots_Dataset_SmolLM3-3B-Base.smollm3-3b-blindspots
SmolLM3-3B Blind Spot Dataset
Tested Model
HuggingFaceTB/SmolLM3-3B
— a raw pretrained base LLM (no instruction tuning) released July 8 2025 with 3B parameters.
How the Model Was Loaded
Loaded on a free Colab T4 GPU in 4-bit NF4 quantisation with bitsandbytes:
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch
MODEL_ID = "HuggingFaceTB/SmolLM3-3B"
bnb_config = BitsAndBytesConfig(
load_in_4bit=True… See the full description on the dataset page: https://huggingface.co/datasets/Abdelrahman350/smollm3-3b-blindspots.Blind_Spots_of_SmolLM3-3B
Dataset Summary
This dataset documents 10 cases where a model produces incoherent outputs on linguistically non-trivial tasks. Each data point consists of an input, the expected correct output, and the model's actual (flawed) output, along with a diagnosis of the failure mode.
The cases span six languages (English, French, German, Spanish, Italian, Portuguese) and cover distinct classes of linguistic difficulty: pragmatics, polysemy, idiomatic reasoning, garden-path syntax, double… See the full description on the dataset page: https://huggingface.co/datasets/Nusrat-Lia/Blind_Spots_of_SmolLM3-3B.GPQA-diamond_SmolLM3-3B_testdetails_HuggingFaceTB__SmolLM3-3B_private
Dataset Card for Evaluation run of HuggingFaceTB/SmolLM3-3B
Dataset automatically created during the evaluation run of model HuggingFaceTB/SmolLM3-3B.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/smol-course/details_HuggingFaceTB__SmolLM3-3B_private.details_pmakiela__SmolLM3-3B-SFT-v1_4_private
Dataset Card for Evaluation run of pmakiela/SmolLM3-3B-SFT-v1_4
Dataset automatically created during the evaluation run of model pmakiela/SmolLM3-3B-SFT-v1_4.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/pmakiela/details_pmakiela__SmolLM3-3B-SFT-v1_4_private.smollm3-3b-base-blindspots
SmolLM3-3B-Base — Blind Spots Dataset
This dataset contains 10 diverse input-output pairs where the base language model
HuggingFaceTB/SmolLM3-3B-Base
produces incorrect predictions under greedy decoding. Each row records the exact prompt fed
to the model, the correct expected answer, and what the model actually generated — along with
a description of the error type.
Model Tested
Field
Value
Model
HuggingFaceTB/SmolLM3-3B-Base
Parameters
3 billion… See the full description on the dataset page: https://huggingface.co/datasets/Dhruba461/smollm3-3b-base-blindspots.smollm3-3b-base-blind-spots
Blind Spots of SmolLM3-3B-Base
This dataset contains 15 diverse examples where the base language model HuggingFaceTB/SmolLM3-3B-Base produces incorrect, repetitive, or off‑task outputs. It was created as part of the Fatima Fellowship technical challenge.
Model
Name: HuggingFaceTB/SmolLM3-3B-Base
Type: Decoder‑only transformer (base model, not instruction‑tuned)
Parameters: 3B
Link: https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base
Methodology
I loaded the… See the full description on the dataset page: https://huggingface.co/datasets/AyshSaleem/smollm3-3b-base-blind-spots.details_pmakiela__SmolLM3-3B-SFT-v1_2_private
Dataset Card for Evaluation run of pmakiela/SmolLM3-3B-SFT-v1_2
Dataset automatically created during the evaluation run of model pmakiela/SmolLM3-3B-SFT-v1_2.
The dataset is composed of 1 configuration, each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/pmakiela/details_pmakiela__SmolLM3-3B-SFT-v1_2_private.pairwise-gpt4.1-vs-smollm3-3bsmollm3-3b-base-blind-spots
SmolLM3-3B-Base Blind Spots
Title & Overview
A curated set of failure cases for HuggingFaceTB/SmolLM3-3B-Base, showcasing blind spots discovered while probing the 3B-parameter base pre-training checkpoint released in July 2025. Each entry captures a prompt, the expected aligned behaviour, and the model's actual output. The dataset illustrates common failure patterns observed when probing the base model without any instruction tuning, RLHF, or safety fine-tuning applied.… See the full description on the dataset page: https://huggingface.co/datasets/aneeshadas02/smollm3-3b-base-blind-spots.smollm3-3b-dmmath-tracesSmolLM3-3B-customerservice-LLM-as-a-judge-data