전체 검색
AI 모델 2119
- rtdetr_v2_r50vd↗
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 RT-DETRv2 consistently outperforms its predecessor across all model sizes while maintaining the same real-time speeds.
- sam2.1_hiera_tiny↗
danelcsb
- minimax-h3-nvfp4↗
MATLOWAI
An NVFP4 quantisation of the MiniMax H3 pruned FL2VA diffusion model for ComfyUI. Every one of the 200 block linears (qkv, out, fc1, fc2 in all 50 blocks) is stored as fp4 e2m1 with fp8 e4m3 block scales of 16 and one fp32 per-tensor scale; embeds, token refiner, norms and heads stay bf16. On Blackwell (sm120) the GEMMs run natively on the fp4 tensor cores. **Modification notice (required by the license): this repository contains a modified version of MiniMax H3. The modification is post-training weight quantisation of the block linears to NVFP4, performed 2026-08-19. Built from `diffusion_models/minimax_h3_fl2va_pruned_bf16.safetensors` in Comfy-Org/MiniMax-H3, revision `3f57e8291d2ef846f9a074b1b76d2767db434abe`.** Runs on stock ComfyUI, no custom nodes required: the file carries per-layer `comfy_quant` metadata, the same mechanism as the NVFP4 text encoder that Comfy-Org already ships.
- xtremedistil-l6-h256-zeroshot-v1.1-all-33↗
MoritzLaurer
This model was fine-tuned using the same pipeline as described in the model card for MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 and in this paper. The foundation model is microsoft/xtremedistil-l6-h256-uncased. The model only has 22 million backbone parameters and 30 million vocabulary parameters. The backbone parameters are the main parameters active during inference, providing a significant speedup over larger models. The model is 25 MB small. This model was trained to provide a very small and highly efficient zeroshot option, especially for edge devices or in-browser use-cases with transformers.js.
- gte-large-en-v1.5↗
Alibaba-NLP
We introduce `gte-v1.5` series, upgraded `gte` embeddings that support the context length of up to **8192**, while further enhancing model performance. The models are built upon the `transformer++` encoder backbone (BERT + RoPE + GLU). The `gte-v1.5` series achieve state-of-the-art scores on the MTEB benchmark within the same model size category and prodvide competitive on the LoCo long-context retrieval tests (refer to Evaluation). We also present the `gte-Qwen1.5-7B-instruct`, a SOTA instruction-tuned multi-lingual embedding model that ranked 2nd in MTEB and 1st in C-MTEB.
- codesage-large-v2↗
codesage
CodeSage is a family of open code embedding models with an encoder architecture that supports a wide range of source code understanding tasks. It was initially introduced in the paper: For this V2 model, we enhanced semantic search performance by improving the quality of the contrastive learning data through consistency filtering. Starting from the pretrained checkpoint (trained with both Masked Language Modeling (MLM) and deobfuscation Section 3.1) from our V1 model training (Zhang et al., 2023), we applied contrastive learning with the filtered data. Unlike the V1 model, we extracted the initial set of (text, code) pairs—specifically, summaries and function/class bodies—from The Stack V2 data instead of using the V1 data. We employed simple rule-based filtering as detailed in our previous work. We then applied consistency filtering to further refine the data. While using The Stack V2 resulted in minor performance boosts on downstream tasks, the majority of the performance improvements came from the consistency filtering. This pretrained checkpoint is the same as those used by our V1 model (codesage/codesage-small, which is trained on The Stack data. The constative learning data are extracted from The Stack V2. Same as our V1 model, we supported nine languages as follows: c, c-sharp, go, java, javascript, typescript, php, python, ruby.
- Sam-flash-mini-v1-GGUF↗
mradermacher
- slimsam-77-uniform↗
nielsr
- zerank-1-small-reranker↗
zeroentropy
This 1.7B reranker is the smaller version of our flagship model zeroentropy/zerank-1. Though the model is over 2x smaller, it maintains nearly the same standard of performance, continuing to outperform other popular rerankers, and displaying massive accuracy gains over traditional vector search. We release this model under the open-source Apache License 2.0, in order to support the open-source community and push the frontier of what's possible with open-source models. NDCG@10 scores between `zerank-1-small` and competing closed-source proprietary rerankers. Since we are evaluating rerankers, OpenAI's `text-embedding-3-small` is used as an initial retriever for the Top 100 candidate documents.