ramithuh/rfdiffusion-webgpu
AI model by ramithuh
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Original RFdiffusion Baseckpt.pt, upstream commit 86507b6538f51fce57b5a72477165f03999ed7ae. This directory contains a standalone ES module implementation of the learned denoiser and a reverse SE(3) sampler. Runtime imports are local modules only. Python, DGL, e3nn, Node and Playwright are development/oracle tools only. Validation status is recorded in fixtures/. Do not interpret an individual kernel or denoiser check as a release pass. npm test fails if any required fixture, weights, hardware adapter, coordinate comparison, or browser contract is unavailable. The test matrix compares each precision to the same dequantized weights running through the original PyTorch/DGL model. Quantization error against the unquantized model is reported separately. From this directory, run bash tools/bootstrap.sh. All downloaded source, Python packages, model weights, binaries and browser profiles stay under this directory. The bootstrap pins upstream, installs the versions in tools/requirements-export.txt, verifies the checkpoint, exports all three bundles, and regenerates the fixtures. Downloading dependencies requires network access. The hardware harness…
Read the full model card ↗ · Preview checked 2026-11-22T08:45:13.504Z
Inside the original model card — Document outline
- Original RFdiffusion: browser port
- Reproduce
- Checkpoint and export
- Architecture audit
- Runtime API
- Verification artifacts
- Demo and vendor integration
- Measured validation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ramithuh/rfdiffusion-webgpu is a task-unspecified model repository published by ramithuh on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-11-22T06:53:59.000Z
- Last modified
- 2026-11-22T06:54:07.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-22T07:03:33.420Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.