CoolFace
13 shown

datasets

Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.

modalityAllTextImageAudioTabularVideo
taskAllText generationQuestion answeringImage classificationSpeech
sizeAllUnder 1K1K – 10K100K – 1M1M – 10M
formatAllParquetJSONCSVWebDataset
sortTrendingMost likedMost usedRecently updatedNewest
Clear all
01Alhibb /smollm2-blind-spots SmolLM2-1.7B Blind Spots Dataset This dataset contains 10 diverse examples where the SmolLM2-1.7B base model makes incorrect predictions or demonstrates "blind spots". Model Tested Model: SmolLM2-1.7B Parameters: 1.7 Billion Type: Base (Pre-trained) How to Load the Model The model was loaded using the transformers library in Python. import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "HuggingFaceTB/SmolLM2-1.7B" tokenizer =… See the full description on the dataset page: https://huggingface.co/datasets/Alhibb/smollm2-blind-spots.texttext-generationn<1K0 likes17 downloads7mo agoHugging Face02sarapatel /smollm2-blind-spots SmolLM2-1.7B Blind Spots Dataset Overview This dataset documents 10 diverse failure cases ("blind spots") discovered while probing HuggingFaceTB/SmolLM2-1.7B — a pure base (pre-trained only, no instruction tuning) language model with 1.7 billion parameters, released by HuggingFace in September 2024. Model Tested Model card: HuggingFaceTB/SmolLM2-1.7B Paper: https://arxiv.org/abs/2502.02737v1 GitHub: https://github.com/huggingface/smollm Parameters: 1.7B… See the full description on the dataset page: https://huggingface.co/datasets/sarapatel/smollm2-blind-spots.textn<1K0 likes15 downloads7mo agoHugging Face03mirackchuks /smollm2-blind-spots Model Tested HuggingFaceTB/SmolLM2-1.7B How I loaded it Used HuggingFace Transformers with AutoModelForCausalLM on Google Colab (T4 GPU, float16). Greedy decoding (do_sample=False) for reproducibility. View Colab Notebook Blind Spots Found The model struggled with: multi-step arithmetic, low-resource languages (Yoruba), African geographic knowledge, code generation, and logical reasoning. Fine-tuning Dataset Recommendation GSM8K / MATH for… See the full description on the dataset page: https://huggingface.co/datasets/mirackchuks/smollm2-blind-spots.texttext-generationn<1K0 likes8 downloads7mo agoHugging Face04Suzyloubna /SmolLM2-1.7B-blind-spots SmolLM2-1.7B Blind Spots Dataset Model Tested HuggingFaceTB/SmolLM2-1.7Bhttps://huggingface.co/HuggingFaceTB/SmolLM2-1.7B A 1.7B parameter base language model (not instruction-tuned). How I Loaded the Model from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_name = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name, dtype=torch.float32)… See the full description on the dataset page: https://huggingface.co/datasets/Suzyloubna/SmolLM2-1.7B-blind-spots.textn<1K0 likes7 downloads7mo agoHugging Face05shallou /smollm2-blind-spots SmolLM2-1.7B Blind Spots Dataset Overview This dataset was created as part of a technical challenge to identify the blind spots of a frontier base language model. We selected SmolLM2-1.7B, a base model released by HuggingFace in late 2024, and tested it on 10 diverse prompts to find where it makes incorrect predictions. Model Tested HuggingFaceTB/SmolLM2-1.7B Parameters: 1.7 Billion Type: Base language model (not fine-tuned for chat or specific tasks)… See the full description on the dataset page: https://huggingface.co/datasets/shallou/smollm2-blind-spots.textn<1K0 likes7 downloads6mo agoHugging Face06WaveOAK /smollm2-nigerian-cultural-blindspotsProject: Blind Spots of Frontier Models (SmolLM2-1.7B) Model Tested SmolLM2-1.7B Loading Code Python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_id = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16) Discussion of Errors The model struggles with cultural semiotics and West African regional dialects (Pidgin). It tends to… See the full description on the dataset page: https://huggingface.co/datasets/WaveOAK/smollm2-nigerian-cultural-blindspots.textn<1K0 likes5 downloads6mo agoHugging Face07medaminerag /smollm2_blindspotstextn<1K0 likes4 downloads7mo agoHugging Face08Suman989 /smollm2-microbiology-hallucinations SmolLM2 Blind Spot Audit — Microbiology & Nepal Community Health Triage Overview This dataset contains 10 manually audited prompt-output pairs from HuggingFaceTB/SmolLM2-1.7B (base model, not instruct), testing its performance on two domain-specific categories: Microbiology laboratory protocols — Gram staining, serial dilution, PCR parameters, selective media interpretation Community health triage in Nepal — FCHV danger sign protocols, MUAC malnutrition thresholds… See the full description on the dataset page: https://huggingface.co/datasets/Suman989/smollm2-microbiology-hallucinations.textn<1K0 likes4 downloads6mo agoHugging Face09Sarah-2002 /smollm2-blindspotstextn<1K0 likes3 downloads7mo agoHugging Face10Sumannnnn12345678 /smollm2-blindspots SmolLM2-1.7B Blind Spots Dataset Model Tested HuggingFaceTB/SmolLM2-1.7B A 1.7B parameter base language model released in 2024 by HuggingFace. How I Loaded the Model Loaded in Google Colab (T4 GPU, free tier) using the following code: from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id… See the full description on the dataset page: https://huggingface.co/datasets/Sumannnnn12345678/smollm2-blindspots.textn<1K0 likes3 downloads5mo agoHugging Face11kashfameen /smolLM2-blindspots-kashaf Blind Spots of HuggingFaceTB/SmolLM2-1.7B Model Tested Model: HuggingFaceTB/SmolLM2-1.7B Release date: December 2024 Parameters: 1.7B Type: Base model (not fine-tuned) How I Loaded the Model I used Google Colab with a T4 GPU. Here is the code: from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_name = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(… See the full description on the dataset page: https://huggingface.co/datasets/kashfameen/smolLM2-blindspots-kashaf.textn<1K0 likes2 downloads7mo agoHugging Face12Jamshed18 /smollm2-blind-spots SmolLM2-1.7B Blind Spots Dataset Model Tested HuggingFaceTB/SmolLM2-1.7B A 1.7B parameter base language model trained by HuggingFace. It is NOT fine-tuned for instruction following or chat — it is a raw base model that completes text. How I Loaded the Model from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_name = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model =… See the full description on the dataset page: https://huggingface.co/datasets/Jamshed18/smollm2-blind-spots.textn<1K0 likes1 downloads7mo agoHugging Face13Ngongbi /smollm2-blind-spots SmolLM2-1.7B Blind Spots Dataset Model Tested Model: HuggingFaceTB/SmolLM2-1.7B Link: https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B Parameters: 1.7B Type: Base model (not finetuned) How I Loaded the Model !pip install transformers torch from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_name = "HuggingFaceTB/SmolLM2-1.7B" tokenizer = AutoTokenizer.from_pretrained(model_name) model =… See the full description on the dataset page: https://huggingface.co/datasets/Ngongbi/smollm2-blind-spots.textn<1K0 likes6mo agoHugging Face

Listings come live from the Hugging Face Hub API. CoolFace does not host these files.