WaveOAK/smollm2-nigerian-cultural-blindspots

Domain:

natural language processing

Record type:

dataset

Creator:

Wav

Host:

Project: 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

saaga/yoruba-cultural-reasoning-blindspots

# Yoruba Cultural Reasoning Blind Spots in Frontier Models ## Overview This dataset captures the "b

zox-BT/gemma-2b-cameroon-cultural-blindspots

This dataset highlights the "blind spots" of the Google Gemma-2-2b base model regarding Cameroonian

SmolLM2 Blind Spots

HuggingFaceTB/SmolLM2-1.7B Used HuggingFace Transformers with AutoModelForCausalLM on Google Colab

Kibalama/smollm2-finetune-eng-2-luganda

kedhamyas/my-blindspots-dataset

This dataset was created to probe blind spots in a small, recently released base language model by f

Chiz/omniASR-igbo-blindspots

This dataset investigates three interrelated questions about multilingual ASR performance on tonal l

WaveOAK/smollm2-nigerian-cultural-blindspots

Domain:

Record type:

Visit

Tasks