datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
lfm25-blind-spots
LFM2.5-1.2B-Base Blind Spots
Model Tested
LiquidAI/LFM2.5-1.2B-Base
LFM2.5-1.2B-Base is a 1.2B parameter hybrid base model by Liquid AI, released
January 2026. Unlike most LLMs, it uses a novel non-Transformer architecture
combining multiplicative gates and short convolutions.
How I Loaded the Model
Tested on Google Colab with a free T4 GPU.
!pip install -q transformers==4.55.0 accelerate
import torch
from transformers import AutoTokenizer… See the full description on the dataset page: https://huggingface.co/datasets/Azeez577/lfm25-blind-spots.lfm2.5-1.2b-blindspots
LFM2.5-1.2B-Base Blind Spots Dataset
Model Link: https://huggingface.co/LiquidAI/LFM2.5-1.2B-BaseNotebook Link: https://colab.research.google.com/drive/13sDzKbvsaYxpKwBD-ePktBrDFX2qoPiI?usp=sharing
Model Loading and Inference
I loaded the model in a high-level manner using the pipeline function from the transformers library:
# Loading the model using the pipeline function from the transformers library
from transformers import pipeline
pipe = pipeline("text-generation"… See the full description on the dataset page: https://huggingface.co/datasets/Almaan/lfm2.5-1.2b-blindspots.lfm25-blindspots
LFM2.5-1.2B-Base — Blind Spots Dataset
A curated dataset of 10 diverse input/output pairs where LiquidAI/LFM2.5-1.2B-Base makes incorrect or surprising predictions. Each row includes the input prompt, the expected (correct) output, and the model's actual output, along with a category and explanatory note.
Model Tested
Field
Detail
Model
LiquidAI/LFM2.5-1.2B-Base
Parameters
1.2B
Type
Base (pretrained, not instruction-tuned)
Released
November 2025… See the full description on the dataset page: https://huggingface.co/datasets/SiriusBlu/lfm25-blindspots.homedepot-lfm25-scored