全站搜索

AI 模型 2119

• DFN5B-CLIP-ViT-H-14↗

  apple

  A CLIP (Contrastive Language-Image Pre-training) model trained on DFN-5B. Data Filtering Networks (DFNs) are small networks used to automatically filter large pools of uncurated data. This model was trained on 5B images that were filtered from a pool of 43B uncurated image-text pairs (12.8B image-text pairs from CommonPool-12.8B + 30B additional public image-text pairs). This model has been converted to PyTorch from the original JAX checkpoints from Axlearn (https://github.com/apple/axlearn). These weights are directly usable in OpenCLIP (image + text). - **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification. - **Dataset:** DFN-5b - **Papers:** - Data Filtering Networks: https://arxiv.org/abs/2309.17425 - **Samples Seen:** 39B

• FLUX.1-Kontext-dev-GGUF↗

  bullerwins

  `FLUX.1 Kontext [dev]` is a 12 billion parameter rectified flow transformer capable of editing images based on text instructions. For more information, please read our blog post and our technical report. You can find information about the `[pro]` version in here. 1. Change existing images based on an edit instruction. 2. Have character, style and object reference without any finetuning. 3. Robust consistency allows users to refine an image through multiple successive edits with minimal visual drift. 4. Trained using guidance distillation, making `FLUX.1 Kontext [dev]` more efficient. 5. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 6. Generated outputs can be used for personal, scientific, and commercial purposes, as described in the [FLUX.1 \[dev\] Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev). We provide a reference implementation of `FLUX.1 Kontext [dev]`, as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of `FLUX.1 Kontext [dev]` are encouraged to use this as a starting point.

• Sam-reason-S2.1-i1-GGUF↗

  mradermacher

• Qwen-Image-2.1-Turbo-GGUF↗

  Abiray

  Quantized GGUF weights for Alibaba's official **Qwen-Image-2.1-Turbo** distilled diffusion model. These checkpoints enable lightning-fast text-to-image and image-editing generation in ComfyUI at a fraction of the native VRAM requirement, taking full advantage of 4–8 step Turbo sampling. All models were converted using `ComfyUI-GGUF` tools and quantized using a patched multi-threaded `llama-quantize` build natively supporting the 297-tensor `qwen_image` architecture.

• Intern-S1-mini↗

  internlm

  We introduce **Intern-S1-mini**, a lightweight open-source multimodal reasoning model based on the same techniques as **Intern-S1**. Built upon an 8B dense language model (Qwen3) and a 0.3B Vision encoder (InternViT), Intern-S1-mini has been further pretrained on **5 trillion tokens** of multimodal data, including over **2.5 trillion scientific-domain tokens**. This enables the model to retain strong general capabilities while excelling in specialized scientific domains such as **interpreting chemical structures, understanding protein sequences, and planning compound synthesis routes**, making Intern-S1-mini to be a capable research assistant for real-world scientific applications. We evaluate the Intern-S1-mini on various benchmarks including general datasets and scientific datasets. We report the performance comparison with the recent VLMs and LLMs below. You can utilize one of the following LLM inference frameworks to create an OpenAI compatible server:

• SAM2.1-Hiera-Tiny-Image-Encoder↗

  litert-community

• Apertus-v1.1-1.5B-Instruct↗

  swiss-ai

  Apertus-v1.1 is a series of highly efficient, 0.5-4B billion parameter language models designed to extend the fully-open and compliant Apertus ecosystem to highly constrained hardware environments. The models rely on a dense transformer architecture featuring grouped-query attention and xIELU activations. Instead of standard pre-training, Apertus-v1.1 models were created using pre-training distillation (PD) from the Apertus-8B-2509 teacher model. They were trained on 1.7T tokens from Phase 5 of the original Apertus data pipeline—the highest quality tier of filtered documents, code, and instruction samples without introducing any new data sources or licenses. Post-training included supervised fine-tuning (SFT) and alignment similar to that of the original Apertus.

• mt5-xl↗

  Google

  mT5 is pretrained on the mC4 corpus, covering 101 languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Cebuano, Chichewa, Chinese, Corsican, Czech, Danish, Dutch, English, Esperanto, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hmong, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Samoan, Scottish Gaelic, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Sotho, Spanish, Sundanese, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, West Frisian, Xhosa, Yiddish, Yoruba, Zulu. **Note**: mT5 was only pre-trained on mC4 excluding any supervised training. Therefore, this model has to be fine-tuned before it is useable on a downstream task.

• t5-3b↗

  google-t5

  1. Model Details 2. Uses 3. Bias, Risks, and Limitations 4. Training Details 5. Evaluation 6. Environmental Impact 7. Citation 8. Model Card Authors 9. How To Get Started With the Model The developers of the Text-To-Text Transfer Transformer (T5) write: > With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task.

• JEV-35B↗

  autotrust

  > [!IMPORTANT] > **Try AutoTrust/GuruSearch live (new, 11 October 2026).** A recommendation and search demo in which every ranking is a > calibrated System 1 decision, made in about half a second: > * **Recommendation:** the latest headlines from 6 news feeds, ranked by importance. > * **Search:** results from Google News, Bing News and Yahoo News re-ranked by relevance, side by side with the > search engines' own order, plus a short answer with citations. **Decision Index 0.3, public suite: 59.73** (our scoring with the kit), against 53.64 for autotrust/JEV-27B-VL on the board. Approximate public vision score **71.94** (our rebuild of the vision benchmarks; JEV-27B-VL 71.67 on the same rebuild, a tie within noise). Median single-request latency 204 ms on one B200 (JEV-27B-VL 271 ms). > [!TIP] > **NVFP4 version: autotrust/JEV-35B-NVFP4**, the same model with its > routed experts in NVFP4: **25.6 GB download, 23 GiB of GPU memory** (bf16: 72 GB, 66 GiB), so it runs on one 32–48 GB > GPU. Decision Index 0.3 public 59.18 (bf16 59.73), vision rebuild 71.23 (bf16 71.94), 96.6 % of the Decision Index > answers identical to bf16, same latency, same `serve.sh` and API.