从语言到影像，从开源到 API。读懂模型能力、比较真实成本，
为你的下一个想法，找到合适的智能引擎。
This repo contains State Of The Art quantized GGUF format model files for Qwen2.5-Coder-32B-Instruct. Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of answers from the CodeFeedback-Filtered-Instruction dataset. These quantised GGUFv3 files are compatible with llama.cpp from February 27th 2024 onwards, as of commit 0becb22
译文排队中 · 当前显示来源原文
This repo contains State Of The Art quantized GGUF format model files for Qwen2.5-Coder-7B-Instruct. Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of answers from the CodeFeedback-Filtered-Instruction dataset. These quantised GGUFv3 files are compatible with llama.cpp from February 27th 2024 onwards, as of commit 0becb22
译文排队中 · 当前显示来源原文
This repo contains State Of The Art quantized GGUF format model files for Qwen3-Coder-30B-A3B-Instruct. Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of answers from the CodeFeedback-Filtered-Instruction dataset. These quantised GGUFv3 files are compatible with llama.cpp from April 9th 2025 onwards, as of commit d3bd719
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
--- license: apache-2.0 language: - en tags: - fill-mask - transformers - safetensors - modernbert - cybersecurity - CiscoAI - code - CTI datasets: - custom library_name: transformers pipeline_tag: fill-mask model-index: - name: SecureBERT2.0-base results: [] base_model: - answerdotai/ModernBERT-base --- SecureBERT 2.0 Base is a domain-specific transformer model optimized for cybersecurity tasks. It extends the ModernBERT architecture with cybersecurity-focused pretraining to produce contextualized embeddings for both technical text and code. SecureBERT 2.0 supports tasks like masked language modeling, semantic search, named entity recognition, vulnerability detection, and code analysis. SecureBERT 2.0 Base is designed for **deep contextual understanding of cybersecurity language and code**. It leverages domain-specific pretraining on a large, heterogeneous corpus covering threat reports, blogs, documentation, and codebases, making it effective for reasoning across natural language and programming syntax.
译文排队中 · 当前显示来源原文
The **SecureBERT 2.0 Bi-Encoder** is a cybersecurity-domain sentence-similarity and document-embedding model fine-tuned from SecureBERT 2.0. It independently encodes queries and documents into a shared vector space for **semantic search**, **information retrieval**, and **cybersecurity knowledge retrieval**. The Bi-Encoder encodes queries and documents **independently** into a joint vector space. This architecture enables scalable **approximate nearest-neighbor search** for candidate retrieval and semantic ranking. The model was optimized to maximize semantic similarity between relevant cybersecurity text pairs using contrastive learning.
译文排队中 · 当前显示来源原文
The **SecureBERT 2.0 Cross-Encoder** is a cybersecurity domain-specific model fine-tuned from SecureBERT 2.0. It computes **pairwise similarity scores** between two texts, enabling use in **text reranking, semantic search, and cybersecurity intelligence retrieval** tasks. Can be integrated into: - Cyber threat intelligence search engines - SOC automation pipelines - Cybersecurity knowledge graph enrichment - Threat hunting and incident response systems The model reflects the distribution of cybersecurity-related data used during fine-tuning. Potential risks include: - Overrepresentation of specific malware, technologies, or threat actors - Bias toward technical English sources - Reduced performance on non-English or mixed technical/natural text
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
This is multilingual Distil-Bert model sequence classifier trained based on JIGSAW Toxic Comment Classification Challenge dataset.
译文排队中 · 当前显示来源原文
This is multilingual XLM-Roberta model sequence classifier fine tunned and based on Cardiff NLP Group sentiment classification model.
译文排队中 · 当前显示来源原文
Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
This is a direct GGUF conversion of black-forest-labs/FLUX.1-dev As this is a quantized model not a finetune, all the same restrictions/original license terms still apply. The model files can be used with the ComfyUI-GGUF custom node.
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
This is a direct GGUF conversion of black-forest-labs/FLUX.1-schnell The model files can be used with the ComfyUI-GGUF custom node. Place model files in `ComfyUI/models/unet` - see the GitHub readme for further install instructions.
译文排队中 · 当前显示来源原文
This is a direct GGUF conversion of black-forest-labs/FLUX.2-dev. The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders: > [!NOTE] > As with Qwen-Image, Q5_K_M, Q4_K_M, Q3_K_M, Q3_K_S and Q2_K have some extra logic as to which blocks to keep in high precision. > > The logic is partially based on guesswork, trial & error, and the graph found in the readme for Freepik/flux.1-lite-8B (which in turn quotes this blog by Ostris)
译文排队中 · 当前显示来源原文
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Place model files in `ComfyUI/models/diffusion_models` - see the GitHub readme for further install instructions.
译文排队中 · 当前显示来源原文
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.
译文排队中 · 当前显示来源原文
NOTE: Hunyuan recently replaced the original model in the repo above with a **new and updated version** - the files in this repo have been reconverted and replaced. If you want to test against the original models, you can find them on this branch 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.
译文排队中 · 当前显示来源原文
可以调整厂商、分类或输入输出条件；新模型正持续收录。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。
