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 model has been pushed to the Hub using the PytorchModelHubMixin integration: - Library: https://github.com/lpiccinelli-eth/UniDepth - Docs: [More Information Needed]
译文排队中 · 当前显示来源原文
This model has been pushed to the Hub using the PytorchModelHubMixin integration: - Library: https://github.com/lpiccinelli-eth/UniDepth - Docs: [More Information Needed]
译文排队中 · 当前显示来源原文
This model has been pushed to the Hub using the PytorchModelHubMixin integration: - Library: https://github.com/lpiccinelli-eth/UniDepth - Docs: [More Information Needed]
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
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 model has been pushed to the Hub using the PytorchModelHubMixin integration: - Library: https://github.com/lpiccinelli-eth/UniK3D - Docs: [More Information Needed]
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
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
f2k_anything2real.safetensors is more 3D like version f2k_anything2real_a.safetensors based on f2k_anything2real.safetensors to adjust the realistic style I'm excited to share the new version of Anything2Real family, Anything2Real 2601 A. Anything2Real 2601 A is an adjusted version based on Anything2Real 2601 and remixed the layer weight of anything2real alpha. Anything2Real 2601 is kinda weak of eyes transformation and anything2real alpha is quite good at light and shadow but weak at color. Anything2Real 2601 A is a more balanced version between "respect to original" and "realistic environemnt" **Alpha Dataset**: lrzjason/Anything2Real_demo_dataset
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
LLäMmlein 1B is a German LLaMa model trained from scratch using our adapted Tinyllama codebase on the German portion of RedPajama V2. To enhance data quality, we additionally deduplicated the dataset on paragraph level and filtered it using a token-to-word ratio filter. The resulting dataset can be found here. You can use LLäMmlein with the `transformers` library. (Optional: install `flash-attn` to achieve highest efficiency.) In addition to the final model checkpoint, we publish intermediate checkpoints throughout the full training process as unique branches in this repository. A specific checkpoint can be loaded like this:
译文排队中 · 当前显示来源原文
This is a German Tinyllama 1B language model trained from scratch using the Tinyllama codebase on the German portion of RedPajama V2. Find more details on our page and our preprint! We evaluated our results on the SuperGLEBer benchmark. Data Take Down
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
ModernGBERT 134M is a German ModernBERT language model with 134 million parameters and a native context length of up to 8,192 tokens. This model follows the same BERT-style architecture and training procedure as the ModernBERT codebase. ModernGBERT 134M has been pre-trained on 470 billion tokens from the German portion of RedPajama V2, a subset of the same training dataset used for our LLäMmlein decoder family. You can use ModernGBERT with the `transformers` library from version v4.48.0 onwards. (Optional: install `flash-attn` to achieve highest efficiency.) Since ModernGBERT 134M is a Masked Language Model (MLM), you can load it via `AutoModelForMaskedLM`. For downstream tasks such as classification, retrieval, or QA, fine-tune the model by following standard BERT fine-tuning recipes.
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
Experimental GGUF weights for running **GLM-5.3-Flash** on a normal PC with the LightTransport Strata fork: expert sidecars and a complete full model for a 128 GB host with a 16 GB NVIDIA GPU, a smaller REAP-224 model, and a complete REAP-50 model for a 64 GB host with a 16 GB AMD GPU. The sidecars requantize routed expert gate/up weights from IQ2_XS to Q2_K and down weights from IQ3_XXS to Q3_K; this changes weight values and is neither a lossless repack nor a fine-tune. REAP-224 keeps 224 of 288 routed experts per layer; REAP-50 keeps 144. Read the quality numbers below before choosing a model. Current measurements, setup for one and two GPUs, and context-length limits are in `docs/GLM53F_RELEASE.md` on the fork's `glm53f` branch; bringing it up on other hardware is described in `docs/GLM53F_NEW_HARDWARE.md`. The conversion recipe is `docs/GLM_RELEASE_Q2Q3.md`. **On a 128 GB machine use `GLM-5.3-Flash-Q23-FP8-assembled.gguf`** (or `experts-q23-fp8.gguf` with the Unsloth shards); **on a 64 GB machine use `reap50/GLM-5.3-Flash-REAP50-Q23-FP8-assembled.gguf`.** Their routed experts have the same types as Q23 (Q2_K gate/up, Q3_K down) but are quantized once, directly from the official FP8 weights, instead of from Unsloth's 2-bit experts (REAP-50: from its Q4_K_M experts). Measured against exact logits of the FP8 release on 16 held-out sequences (8,192 tokens):
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
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
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。
