Ornith-1.5-35B-A3B-MagicQuant-GGUF
lmcoleman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。
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
This is a LLaMA 3 Youko qlora fine-tune, created using a new version of the VNTL dataset. The purpose of this fine-tune is to improve performance of LLMs at translating Japanese visual novels to English. For this new version of VNTL 8B, I've rebuilt and expanded VNTL's dataset from the groud up, and I'm happy to say it performs really well, outperforming the previous version when it comes to accuracy and stability, it makes far fewer mistakes than it even when running at high temperatures (though I still recommend temperature 0 for the best accuracy). Some major changes in this version: - **Switched to the default LLaMA3 prompt format since people had trouble with the custom one** - **Added proper support for multi-line translations** (the old version only handled single lines) - Overall better translation accuracy
翻訳待ち・原文を表示
GGUF quantizations of wangzhang/Qwen3.6-35B-A3B-abliterated-v2, itself an abliterated (refusal-suppressed) derivative of Qwen/Qwen3.6-35B-A3B. The quantizations were made with llama.cpp. This repository is an independent redistribution and is not an official release of Qwen or of the abliteration author. The abliterated checkpoint contains the language model only. The included `mmproj-Qwen3.6-35B-A3B-F16.gguf` was converted from the vision tower of the base model `Qwen/Qwen3.6-35B-A3B`, so it is not abliterated and was not modified. Image input through this projector has not been tested for this release. To run text only, simply do not pass `--mmproj`. In llama.cpp the projector can be kept on the CPU with `--no-mmproj-offload`. The governing upstream license is the Apache License 2.0. A copy is included in `LICENSE` (identical to the copy distributed with the source checkpoint). All applicable upstream copyright, attribution and other license terms remain in effect, and this repository grants no rights beyond those provided by the upstream license. Downstream users must preserve the applicable license and attribution notices.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
> [!IMPORTANT] > 🌟 **The core work on this project is led by Glint Lab.** > For an interactive online experience, visit **ve2s.ai**. A multimodal vision-language model that handles **single images, multi-image, and video** inputs, built on a Qwen3-8B language backbone with a OneVision-style vision encoder. The model is distributed as a HuggingFace `transformers` checkpoint with custom code (`trust_remote_code=True`).
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
> [!IMPORTANT] > 🌟 **The core work on this project is led by Glint Lab.** > For an interactive online experience, visit **ve2s.ai**. LLaVA-OneVision-1.5 is a fully open-source family of large multimodal models (LMMs) built to democratize multimodal training. Trained on native‑resolution images, it delivers state‑of‑the‑art performance at substantially lower cost. The project also releases high‑quality pretraining and SFT data, a complete and efficient training framework with recipes and configs, and comprehensive logs to support transparent, reproducible research. - The model leads on multiple multimodal benchmarks and generally surpasses Qwen2.5-VL. - Training on native-resolution images significantly improves its visual understanding. Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
Play with the model on the LLaVA OneVision Chat. 1. Model Summary 2. Use 3. Limitations 4. Training 5. License 6. Citation The LLaVA-OneVision models are 0.5/7/72B parameter models trained on LLaVA-OneVision, based on Qwen2 language model with a context window of 32K tokens.
翻訳待ち・原文を表示
The LLaVA-Video models are 7/72B parameter models trained on LLaVA-Video-178K and LLaVA-OneVision Dataset, based on Qwen2 language model with a context window of 32K tokens. The model was trained on LLaVA-Video-178K and LLaVA-OneVision Dataset, having the ability to interact with images, multi-image and videos, but specific to videos. We provide the simple generation process for using our model. For more details, you could refer to Github.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。