Tasks and inputs
facebook/vjepa2-vitg-fpc64-384 is listed for Video classification. It accepts video and produces label. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 7, 2026
facebook/vjepa2-vitg-fpc64-384 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
facebook/vjepa2-vitg-fpc64-384 is a Hugging Face repository returned by the public Video classification task feed. Its recorded download count is 6,824 and it has 44 likes when the repository snapshot was collected. Popularity is useful for discovery, but it is not a performance ranking or a guarantee of suitability.
This record is categorized for Video classification. A task category describes the intended machine-learning problem; it does not prove that every version, checkpoint, quantization, or deployment method produces the same quality. Teams should read the model card and test representative inputs before choosing it.
The public repository lists transformers as its library metadata. Its recorded tags include transformers, safetensors, vjepa2, feature-extraction, video, video-classification, license:apache-2.0, endpoints_compatible. These source details are retained so readers can trace this directory entry back to the repository instead of relying on copied descriptions.
Use inputs that resemble deployment traffic, including difficult and out-of-domain cases. Compare output correctness, the response format, latency and memory requirements with a simple baseline under the same conditions.
The Hugging Face task assignment records video as input and label as output for facebook/vjepa2-vitg-fpc64-384. This interface summary comes from the repository’s recorded Video classification task classification. It helps readers distinguish a text, image, audio, video, document, embedding, or prediction workflow without inferring undocumented API behavior. Model wrappers can expose different preprocessing and response formats, so verify the upstream model card and the exact runtime before deployment.
Explore facebook models and the video classification collection. Use the comparison tool to inspect a second candidate.
Compare the model on the work you need to complete.
facebook/vjepa2-vitg-fpc64-384 is listed for Video classification. It accepts video and produces label. Use the publisher’s input format and preprocessing for your chosen deployment.
Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
facebook/timesformer-base-finetuned-k400 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
facebook/timesformer-base-finetuned-k600 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
facebook/vjepa2-vitg-fpc64-256 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
facebook/vjepa2-vitl-fpc16-256-ssv2 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
facebook/vjepa2-vitl-fpc64-256 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.
google/videoprism-base-f16r288 is a source-linked Hugging Face repository assigned to Video classification. Its recorded task interface accepts video and produces label.