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 is a preview release of the olmOCR model that's fine tuned from Qwen2-VL-7B-Instruct using the olmOCR-mix-0225 dataset. Quick links: - 📃 Paper - 🤗 Dataset - 🛠️ Code - 🎮 Demo The best way to use this model is via the olmOCR toolkit. The toolkit comes with an efficient inference setup via sglang that can handle millions of documents at scale.
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
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
Quantized to FP8 Version of olmOCR-7B-0825, using llmcompressor. This is a release of the olmOCR model that's fine tuned from Qwen2.5-VL-7B-Instruct using the olmOCR-mix-0225 dataset. Quick links: - 📃 Paper - 🤗 Dataset - 🛠️ Code - 🎮 Demo
译文排队中 · 当前显示来源原文
> OLMoE-1B-7B is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in January 2025 (0125) that is 100% open-source. It is an improved version of OLMoE-09-24, see the paper appendix for details. Important branches: - `step1200000-tokens5033B`: Pretraining checkpoint used for annealing. There are a few more checkpoints after this one but we did not use them. - `main`: Checkpoint annealed from `step1200000-tokens5033B` for an additional 100B tokens (23,842 steps). We use this checkpoint for our adaptation (https://huggingface.co/allenai/OLMoE-1B-7B-0125-SFT & https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct). - `fp32`: FP32 version of `main`. The model weights were stored in FP32 during training but we did not observe any performance drop from casting them to BF16 after training so we upload all weights in BF16. If you want the original FP32 checkpoint for `main` you can use this one. You will find that it yields slightly different results but should perform around the same on benchmarks.
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
OLMoE-1B-7B-0125-Instruct January 2025 is post-trained variant of the OLMoE-1B-7B January 2025 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset, and finally RLVR training using this data. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. Check out the OLMoE paper or Tülu 3 paper for more details! OLMo is a series of **O**pen **L**anguage **Mo**dels designed to enable the science of language models. These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs (coming soon), and associated training details. The core models released in this batch include the following: - **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets. - **Language(s) (NLP):** Primarily English - **License:** Apache 2.0 - **Finetuned from model:** allenai/OLMoE-1B-7B-0125-DPO
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。
> OLMoE-1B-7B is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in September 2024 (0924). It yields state-of-the-art performance among models with a similar cost (1B) and is competitive with much larger models like Llama2-13B. OLMoE is 100% open-source. This information and more can also be found on the **OLMoE GitHub repository**. - **Paper**: https://arxiv.org/abs/2409.02060 - **Pretraining** Checkpoints, Code, Data and Logs. - **SFT (Supervised Fine-Tuning)** Checkpoints, Code, Data and Logs. - **DPO/KTO (Direct Preference Optimization/Kahneman-Tversky Optimization)**, Checkpoints, Preference Data, DPO code, KTO code and Logs. Install `transformers` **from source** until a release after this PR & `torch` and run:
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
> OLMoE-1B-7B-Instruct is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in September 2024 (0924) that has been adapted via SFT and DPO from OLMoE-1B-7B. It yields state-of-the-art performance among models with a similar cost (1B) and is competitive with much larger models like Llama2-13B-Chat. OLMoE is 100% open-source. This information and more can also be found on the **OLMoE GitHub repository**. - **Paper**: https://arxiv.org/abs/2409.02060 - **Pretraining** Checkpoints, Code, Data and Logs. - **SFT (Supervised Fine-Tuning)** Checkpoints, Code, Data and Logs. - **DPO/KTO (Direct Preference Optimization/Kahneman-Tversky Optimization)**, Checkpoints, Preference Data, DPO code, KTO code and Logs. Branches: - `main`: Preference tuned via DPO model of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT (`main` branch) - `load-balancing`: Ablation with load balancing loss during DPO starting from the `load-balancing` branch of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT - `non-annealed`: Ablation starting from the `non-annealed` branch of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT which is an SFT of the pretraining checkpoint prior to annealing (branch `step1200000-tokens5033B` of https://hf.co/allenai/OLMoE-1B-7B-0924) - `kto`: Ablation using KTO instead of DPO. This branch is the checkpoint after 5,000 steps with the RMS optimizer. The other `kto*` branches correspond to the other checkpoints mentioned in the paper.
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
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
OlmoEarth-v1_1-Base is a ViT-Base (114M parameters) foundation model for remote sensing tasks over Sentinel-1, Sentinel-2, and Landsat images or image time series. This model is presented in the paper OlmoEarth v1.2: A more efficient family of OlmoEarth models. - GitHub: https://github.com/allenai/olmoearth_pretrain - Paper: https://allenai.org/papers/olmoearth_v1_2
译文排队中 · 当前显示来源原文
OlmoEarth-v1_2-Nano is a ViT-Nano (1.7M parameters) foundation model for remote sensing tasks over Sentinel-1, Sentinel-2, and Landsat images or image time series. If you are interested in computing embeddings with OlmoEarth, or fine-tuning OlmoEarth for a downstream task, see our tutorials: The OlmoEarth model is deployed in the OlmoEarth Platform, a solution that enables any organization to leverage our models and accelerate their mission, without requiring deep AI or engineering expertise. Sign up to get updates and partner access.
译文排队中 · 当前显示来源原文
OlmoEarth-v1_2-Small is a ViT-Small (36M parameters) foundation model for remote sensing tasks over Sentinel-1, Sentinel-2, and Landsat images or image time series, presented in OlmoEarth v1.2: A more efficient family of OlmoEarth models. If you are interested in computing embeddings with OlmoEarth, or fine-tuning OlmoEarth for a downstream task, see our tutorials: The OlmoEarth model is deployed in the OlmoEarth Platform, a solution that enables any organization to leverage our models and accelerate their mission, without requiring deep AI or engineering expertise. Sign up to get updates and partner access.
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。
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。
