# rtdetr-v2-r50-fire-smoke by Fire Viewer: Open-Weight Model Source: https://savrn.com/models/rtdetr-v2-r50-fire-smoke Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve rtdetr-v2-r50-fire-smoke (43M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [rtdetr-v2-r50-fire-smoke on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/rtdetr-v2-r50-fire-smoke/gpus) ## Model Card Two-class visible smoke/flame detector based on PekingU/rtdetrv2r50vd. Conservative historical/reference detector. On the retained independent FireViewer benchmark, COCO mAP50-95 is 0.3502. It remains useful as a reproducible comparator and lower-false-alarm operating reference; public availability does not mean current runtime promotion. Research, evaluation and permitted commercial inference under the checkpoint terms. This model does not determine geographic coordinates, hidden fire origin, a fire perimeter or an emergency decision. Outputs must retain scores/provenance and remain subject to human review. The upstream base model is Apache-2.0. FireViewer checkpoint terms are separate… Excerpt from the card by Fire Viewer, licensed other. ## Configuration Architecture RTDetrV2ForObjectDetection Model type rt_detr_v2 ## Identity and Version Repository fireviewer/rtdetr-v2-r50-fire-smoke Publisher Fire Viewer Task Object detection Modality Image Library transformers Parameters 43M parameters Languages Not stated by the source Revision ffae895563babc51fc022521a480067c0fda30f7 First published 2026-07-26 Last updated 2026-10-05 ## Files and Weights 32 files, 173.4 MB in total. The weights are 2 files totalling 171.5 MB in bin, safetensors. Weights2 files · 171.5 MB Configuration13 files · 241.5 KB Documentation9 files · 18.4 KB Other7 files · 1.6 MB Repository1 file · 1.7 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 171.5 MB | 75aa67a0ed24 | | training_args.bin | Weights | 5.9 KB | 29c44cdc1259 | | MODEL_ARTIFACTS_MANIFEST.json | Configuration | 615 B | — | | TRAINING_DATA_MANIFEST.json | Configuration | 2.0 KB | — | | benchmark/independent-evaluation.json | Configuration | 1.5 KB | — | | config.json | Configuration | 2.8 KB | — | | evaluation/evaluation-plan.json | Configuration | 1.6 KB | — | | evaluation/evaluation-results.json | Configuration | 3.4 KB | — | | evaluation/rtdetr-reproduction.json | Configuration | 8.8 KB | — | | evaluation/run_rtdetr_reproduction.py | Configuration | 16.6 KB | — | | fireviewer_inference.py | Configuration | 4.6 KB | — | | preflight-report.json | Configuration | 20.5 KB | — | | preprocessor_config.json | Configuration | 807 B | — | | trainer_state.json | Configuration | 175.7 KB | — | | training-provenance.json | Configuration | 2.4 KB | — | | CHECKPOINT_LICENSE.md | Documentation | 4.4 KB | — | | CHECKPOINT_RIGHTS.md | Documentation | 2.0 KB | — | | CITATION.md | Documentation | 406 B | — | | COMMERCIAL_USE.md | Documentation | 1.1 KB | — | | MODEL_RIGHTS_POLICY.md | Documentation | 2.4 KB | — | | README.md | Documentation | 5.6 KB | — | | RIGHTS_AND_ATTRIBUTION.md | Documentation | 577 B | — | | THIRD_PARTY_NOTICES.md | Documentation | 264 B | — | | evaluation/CONTRACT-AUDIT-20260728.md | Documentation | 1.6 KB | — | | assets/contract-audit-20260728.png | Other | 207.0 KB | 02ab7a8ad6c2 | | assets/contract-audit-20260728.svg | Other | 101.0 KB | — | | assets/detector-comparison-20260728.png | Other | 112.3 KB | bad54e5d3150 | | assets/detector-comparison-20260728.svg | Other | 73.8 KB | — | | benchmark/benchmark-final.png | Other | 176.5 KB | f80b21520342 | | evaluation/evaluation-selection.jsonl | Other | 880.8 KB | — | | model.safetensors.sha256 | Other | 85 B | — | | .gitattributes | Repository | 1.7 KB | — | ## License and Download License other Access Open weights, no gate Download size 171.5 MB [Download from Fire Viewer](https://huggingface.co/fireviewer/rtdetr-v2-r50-fire-smoke) Released by Fire Viewer through its official repository on Hugging Face. [Read the license](https://huggingface.co/fireviewer/rtdetr-v2-r50-fire-smoke/blob/b16bc79df05a69bfd90a7130d77fdbbd0d556465/CHECKPOINT_LICENSE.md). ## Built From - Derived from [PekingU/rtdetr_v2_r50vd](https://savrn.com/models/rtdetr-v2-r50vd) - Trained on (disclosed) [fireviewer/fire-smoke-detection-corpus-v1](https://savrn.com/datasets/fire-smoke-detection-corpus-v1) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 171.5 MB | | 16-bit | 0.1 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About rtdetr-v2-r50-fire-smoke ### How much GPU memory does rtdetr-v2-r50-fire-smoke need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (43M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run rtdetr-v2-r50-fire-smoke on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### What license is rtdetr-v2-r50-fire-smoke released under? other, as its publisher declares it. Read the license text before commercial use. ## Similar Models Model · Object detection ### [rtdetr_r50vd_coco_o365](https://savrn.com/models/rtdetr-r50vd-coco-o365) [Peking University](https://savrn.com/model-publishers/pekingu) However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy.… Open weights apache-2.0 43M parameters transformers [View model](https://savrn.com/models/rtdetr-r50vd-coco-o365) Model · Object detection ### [rtdetr_r50vd](https://savrn.com/models/rtdetr-r50vd) [Peking University](https://savrn.com/model-publishers/pekingu) However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy.… Open weights apache-2.0 43M parameters transformers [View model](https://savrn.com/models/rtdetr-r50vd) Model · Object detection ### [rtdetr_v2_r50vd](https://savrn.com/models/rtdetr-v2-r50vd) [Peking University](https://savrn.com/model-publishers/pekingu) The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf This is RT-DETRv2 consistently outperforms its predecessor across all… Open weights apache-2.0 43M parameters transformers [View model](https://savrn.com/models/rtdetr-v2-r50vd) Model · Object detection ### [fashion-object-detection](https://savrn.com/models/fashion-object-detection) [Yainage90](https://savrn.com/model-publishers/yainage90) This model is fine-tuned version of microsoft/conditional-detr-resnet-50. You can find details of model in this github repo -> fashion-visual-search And you can find fashion image feature extractor model -> yainage90/fashion-image-feature-extractor This model was trained using a combination of two datasets: modanet and fashionpedia The labels are ['bag', 'bottom', 'dress', 'hat', 'shoes', 'outer', 'top'] In the 96th epoch out of total of 100 epochs, the best score was achieved with mAP 0.7542. Therefore, it is believed that there is a little room for performance improvement. Open weights mit 44M parameters 1,024 tokens transformers [View model](https://savrn.com/models/fashion-object-detection) Model · Object detection ### [conditional-detr-resnet-50](https://savrn.com/models/conditional-detr-resnet-50) [Microsoft](https://savrn.com/model-publishers/microsoft) Conditional DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper Conditional DETR for Fast Training Convergence by Meng et al. and first released in this repository. The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a conditional cross-attention mechanism for fast DETR training. Our approach is motivated by that the cross-attention in DETR relies highly on the content embeddings for localizing the four extremities and… Open weights apache-2.0 44M parameters 1,024 tokens transformers [View model](https://savrn.com/models/conditional-detr-resnet-50) Model · Object detection ### [dab-detr-resnet-50](https://savrn.com/models/dab-detr-resnet-50) [IDEA-Research](https://savrn.com/model-publishers/idea-research) This is the model card of a transformers model that has been pushed on the Hub. Use the code below to get started with the model. This should output The DAB-DETR model was trained on COCO 2017 object detection, a dataset consisting of 118k/5k annotated images for training/validation respectively. Following Deformable DETR and Conditional DETR, we use 300 anchors as queries. We select 300 predicted boxes and labels with the largest classification logits for evaluation as well. We also use focal loss (Lin et al., 2020) with α = 0.25, γ = 2 for classification. The same loss terms are used in bipartite matching and final loss calculating, but with different coefficients. Classification loss… Open weights apache-2.0 44M parameters transformers [View model](https://savrn.com/models/dab-detr-resnet-50) ## Fire Viewer [All models and datasets](https://savrn.com/model-publishers/fireviewer) ## Versions - [ffae895563ba](https://savrn.com/models/rtdetr-v2-r50-fire-smoke/versions/ffae895563ba) · current 2026-10-05 ## Explore More - [All object detection models](https://savrn.com/models/tasks/object-detection) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-05. - [Hugging Face record](https://huggingface.co/fireviewer/rtdetr-v2-r50-fire-smoke) - [How the hub is built](https://savrn.com/model-hub/methodology)