サイト内検索
AI モデル 2119
- Nemotron-Labs-Diffusion-8B↗
NVIDIA
Nemotron-Labs-Diffusion is a tri-mode language model that supports both AR decoding and diffusion-based parallel decoding by simply switching the attention pattern of the same model during inference. The synergy between these two modes enables a third mode, called self-speculation: the same model performs diffusion-based parallel drafting and AR verification with shared KV cache, achieving high acceptance lengths and decoding efficiency. The seamless mode switching by simply changing attention patterns enables high efficiency at different concurrency levels in varying deployment scenarios with one single model. An optional LoRA adatper can be applied to the diffusion drafter in the linear self-speculation mode to further increase the acceptance length: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the bias, explainability, safety & security, and privacy subcards.
- PP-Chart2Table↗
PaddlePaddle
PP-Chart2Table is a SOTA multimodal model developed by the PaddlePaddle team, specializing in chart parsing for both Chinese and English. Its high performance is driven by a novel "Shuffled Chart Data Retrieval" training task, which, combined with a refined token masking strategy, significantly improves its efficiency in converting charts to data tables. The model is further strengthened by an advanced data synthesis pipeline that uses high-quality seed data, RAG, and LLMs persona design to create a richer, more diverse training set. To address the challenge of large-scale unlabeled, out-of-distribution (OOD) data, the team implemented a two-stage distillation process, ensuring robust adaptability and generalization on real-world data. In-house benchmarks demonstrate that PP-Chart2Table not only outperforms models of a similar scale but also achieves performance on par with 7-billion parameter Vision Language Models (VLMs) in critical application scenarios. You can integrate the model inference of PP-Chart2Table into your project. Before running the following code, please download the sample image to your local machine. The ability of a single model is limited. But the pipeline consists of several models can provide more capacity to resolve difficult problems in real-world scenarios.
- codet5p-110m-embedding↗
Salesforce
Compared to the original CodeT5 family (base: `220M`, large: `770M`), CodeT5+ is pretrained with a diverse set of pretraining tasks including _span denoising_, _causal language modeling_, _contrastive learning_, and _text-code matching_ to learn rich representations from both unimodal code data and bimodal code-text data. Additionally, it employs a simple yet effective _compute-efficient pretraining_ method to initialize the model components with frozen off-the-shelf LLMs such as CodeGen to efficiently scale up the model (i.e. `2B`, `6B`, `16B`), and adopts a "shallow encoder and deep decoder" architecture. Furthermore, it is instruction-tuned to align with natural language instructions (see our InstructCodeT5+ 16B) following Code Alpaca. This checkpoint consists of an encoder of CodeT5+ 220M model (pretrained from 2 stages on both unimodal and bimodal) and a projection layer, which can be used to extract code embeddings of 256 dimension. It can be easily loaded using the `AutoModel` functionality and employs the same CodeT5 tokenizer. This checkpoint is trained on the stricter permissive subset of the deduplicated version of the github-code dataset. The data is preprocessed by reserving only permissively licensed code ("mit" “apache-2”, “bsd-3-clause”, “bsd-2-clause”, “cc0-1.0”, “unlicense”, “isc”). Supported languages (9 in total) are as follows: `c`, `c++`, `c-sharp`, `go`, `java`, `javascript`, `php`, `python`, `ruby.`
- mmlw-retrieval-roberta-large-v2↗
sdadas
MMLW (muszę mieć lepszą wiadomość) are neural text encoders for Polish. The second version is based on the same foundational model (polish-roberta-large-v2), but the training process incorporated modern LLM-based English retrievers and rerankers, which led to improved results. This model is optimized for information retrieval tasks. It can transform queries and passages to 1024 dimensional vectors. The model was developed using a two-step procedure: - In the first step, it was initialized with Polish RoBERTa checkpoint, and then trained with multilingual knowledge distillation method on a diverse corpus of 20 million Polish-English text pairs. We utilised stella_en_1.5B_v5 as the teacher models for distillation. - The second step involved fine-tuning the model with contrastrive loss using a dataset consisting of over 4 million queries. Positive and negative passages for each query have been selected with the help of BAAI/bge-reranker-v2.5-gemma2-lightweight reranker. The model supports both information retrieval and semantic textual similarity. For retrieval, queries should be prefixed with **"[query]: "**. For symmetric tasks such as semantic similarity, both texts should be prefixed with **"[sts]: "**. The model achieves **NDCG@10** of **60.71** on the Polish Information Retrieval Benchmark. See PIRB Leaderboard for detailed results.
- PP-OCRv5_mobile_det↗
PaddlePaddle
PP-OCRv5_mobile_det is one of the PP-OCRv5_det series, the latest generation of text detection models developed by the PaddleOCR team. It aims to efficiently and accurately supports the detection of text in diverse scenarios—including handwriting, vertical, rotated, and curved text—across multiple languages such as Simplified Chinese, Traditional Chinese, English, and Japanese. Key features include robust handling of complex layouts, varying text sizes, and challenging backgrounds, making it suitable for practical applications like document analysis, license plate recognition, and scene text detection. The key accuracy metrics are as follow: For details about PaddlePaddle installation, please refer to the PaddlePaddle official website. You can also integrate the model inference of the text detection module into your project. Before running the following code, please download the sample image to your local machine.
- PP-OCRv6_small_det↗
PaddlePaddle
PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. 1. **Unified and Scalable Model Family:** A three-tier OCR model family spanning 1.5M to 34.5M parameters. PP-OCRv6_medium achieves 86.2% detection Hmean and 83.2% recognition accuracy, outperforming PP-OCRv5_server by +4.6% and +5.1% respectively. 2. **Lightweight Architectural Innovations:** (i) LCNetV4, a MetaFormer-style lightweight backbone with structural reparameterization; (ii) RepLKFPN, a detection neck with dilated reparameterizable depthwise convolutions; (iii) EncoderWithLightSVTR, a recognition neck with local-global attention and additive skip connections.
- bert-base-japanese-v2↗
tohoku-nlp
This version of the model processes input texts with word-level tokenization based on the Unidic 2.1.2 dictionary (available in unidic-lite package), followed by the WordPiece subword tokenization. Additionally, the model is trained with the whole word masking enabled for the masked language modeling (MLM) objective. The model architecture is the same as the original BERT base model; 12 layers, 768 dimensions of hidden states, and 12 attention heads. The models are trained on the Japanese version of Wikipedia. The training corpus is generated from the Wikipedia Cirrussearch dump file as of August 31, 2020.
- MiniCPM-V-4.6-Thinking-gguf↗
openbmb
> **This repository hosts the GGUF (llama.cpp) quantized version of MiniCPM-V 4.6 Thinking.** For the original BF16 weights and the full model card, please refer to openbmb/MiniCPM-V-4.6-Thinking. **MiniCPM-V 4.6 Thinking** is the long chain-of-thought reasoning variant of MiniCPM-V 4.6. It generates an explicit reasoning trace before producing the final answer, substantially boosting performance on complex multimodal reasoning, math, and OCR-heavy tasks, while keeping the same edge-friendly architecture (SigLIP2-400M vision encoder + Qwen3.5-0.8B LLM) and the mixed 4x/16x visual token compression of MiniCPM-V 4.6. MiniCPM-V 4.6 can be deployed across three mainstream end-side platforms — **iOS, Android and HarmonyOS**. The clips below are raw screen recordings on phone devices without edition.
- LTX-Video-gguf↗
city96
As this is a quantized model not a finetune, all the same restrictions/original license terms still apply. Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.
- pythia-70m-deduped↗
EleutherAI
The *Pythia Scaling Suite* is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two models: one trained on the Pile, and one trained on the Pile after the dataset has been globally deduplicated. All 8 model sizes are trained on the exact same data, in the exact same order. We also provide 154 intermediate checkpoints per model, hosted on Hugging Face as branches. The Pythia model suite was designed to promote scientific research on large language models, especially interpretability research. Despite not centering downstream performance as a design goal, we find the models match or exceed the performance of similar and same-sized models, such as those in the OPT and GPT-Neo suites. Previously, we released an early version of the Pythia suite to the public. However, we decided to retrain the model suite to address a few hyperparameter discrepancies. This model card lists the changes ; see appendix B in the Pythia paper for further discussion. We found no difference in benchmark performance between the two Pythia versions. The old models are still available, but we suggest the retrained suite if you are just starting to use Pythia. **This is the current release.**