datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
oven-qwen3-vl-eval-traces
OVEN Qwen3-VL Evaluation Traces
Raw evaluation traces from my MSc thesis: Qwen3-VL (2B / 4B / 8B / 32B) sampled
on the OVEN open-domain visual entity recognition task (aligned validation split),
with LM-as-judge verdicts. These are the rollouts behind the thesis's coverage
(pass@k) and specificity results.
Files are grouped by model size (2b/, 4b/, 8b/, 32b/):
file
contents
samples.jsonl
standard sampling: N=256 stochastic rollouts per example, under all_texts… See the full description on the dataset page: https://huggingface.co/datasets/jucamohedano/oven-qwen3-vl-eval-traces.testing_qwen3vl_embeddings
Dataset Card for random_short_videos
This is a FiftyOne dataset with 412 samples.
Installation
If you haven't already, install FiftyOne:
pip install -U fiftyone
Usage
import fiftyone as fo
from fiftyone.utils.huggingface import load_from_hub
# Load the dataset
# Note: other available arguments include 'max_samples', etc
dataset = load_from_hub("harpreetsahota/testing_qwen3vl_embeddings")
# Launch the App
session = fo.launch_app(dataset)… See the full description on the dataset page: https://huggingface.co/datasets/harpreetsahota/testing_qwen3vl_embeddings.testing_qwen3vl_on_video
Dataset Card for harpreetsahota/random_short_videos
This is a FiftyOne dataset with 412 samples.
Installation
If you haven't already, install FiftyOne:
pip install -U fiftyone
Usage
import fiftyone as fo
from fiftyone.utils.huggingface import load_from_hub
# Load the dataset
# Note: other available arguments include 'max_samples', etc
dataset = load_from_hub("harpreetsahota/testing_qwen3vl_on_video")
# Launch the App
session = fo.launch_app(dataset)… See the full description on the dataset page: https://huggingface.co/datasets/harpreetsahota/testing_qwen3vl_on_video.qwen3.5-4b-base-blindspot-samples
Blind Spots of Frontier Models: Qwen3.5-4B-Base
Fatima Fellowship 2026 -- Technical Challenge Report
GitHub: GrantorShadow/Fatima-Fellowship-2026
1. Model Selection
Model: Qwen/Qwen3.5-4B-Base
Property
Value
Parameters
4B
Architecture
Gated DeltaNet hybrid: 8x(3xDeltaNet + FFN + 1xAttention + FFN)
Context Window
262K tokens (claimed)
Type
Base model (no instruction tuning)
Modality
Multimodal (text + vision)
Release
Within last 6 months on Hugging… See the full description on the dataset page: https://huggingface.co/datasets/EtherealGlorious/qwen3.5-4b-base-blindspot-samples.