전체 검색

AI 모델 449

• Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated↗

  huihui-ai

  This is an uncensored version of Qwen/Qwen3-30B-A3B-Instruct-2507 created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. Ablation was performed using a new and faster method, which yields better results. You can use huihui_ai/qwen3-abliterated:30b-a3b-instruct-2507-q4_K_M directly,

• Qwen2.5-VL-3B-Instruct-quantized.w8a8↗

  RedHatAI

  This model was obtained by quantizing the weights of Qwen/Qwen2.5-VL-3B-Instruct to INT8 data type, ready for inference with vLLM >= 0.5.2. This model was created with llm-compressor by running the code snippet below as part a multimodal announcement blog. The model was evaluated using mistral-evals for vision-related tasks and using lm_evaluation_harness for select text-based benchmarks. The evaluations were conducted using the following commands:

• colqwen2.5-v0.2↗

  vidore

  ColQwen is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a Qwen2.5-VL-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository This model takes dynamic image resolutions in input and does not resize them, changing their aspect ratio as in ColPali. Maximal resolution is set so that 768 image patches are created at most. Experiments show clear improvements with larger amounts of image patches, at the cost of memory requirements. Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both *ViDoRe* and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.

• wav2vec2-large-lv60↗

  facebook

  The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. **Abstract** We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.

• Llama-3.3-70B-Instruct-abliterated↗

  huihui-ai

  This is an uncensored version of meta-llama/Llama-3.3-70B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. You can use huihui_ai/llama3.3-abliterated directly, Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.

• Qwen3.5-4B-MLX-4bit↗

  lmstudio-community

  _👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: Qwen **Original model**: Qwen3.5-4B **MLX quantization**: provided by LM Studio team using mlx_vlm LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

• pornworks-real-porn-photo-realistic-nsfw-sdxl-and-pony-chekpoint↗

  Manjushri

  The latest version of the model is always available online at PornWorks.com - best nsfw neural generator We have done a lot of work to create a model that follows the hint perfectly, producing the highest quality NSFW output images even without using ADetailer and Upscaler

• distilbert-base-uncased-go-emotions-onnx↗

  Cohee

  This model is distilled from the zero-shot classification pipeline on the unlabeled GoEmotions dataset using this script. It was trained with mixed precision for 10 epochs and otherwise used the default script arguments. The model can be used like any other model trained on GoEmotions, but will likely not perform as well as a model trained with full supervision. It is primarily intended as a demo of how an expensive NLI-based zero-shot model can be distilled to a more efficient student, allowing a classifier to be trained with only unlabeled data. Note that although the GoEmotions dataset allow multiple labels per instance, the teacher used single-label classification to create psuedo-labels.

• Gemma-SEA-LION-v3-9B-IT↗

  aisingapore

  - **Developed by:** Products Pillar, AI Singapore - **Funded by:** Singapore NRF - **Model type:** Decoder - **Languages supported:** Burmese, Chinese, English, Filipino, Indonesia, Javanese, Khmer, Lao, Malay, Sundanese, Tamil, Thai, Vietnamese - **License:** Gemma Community License We performed instruction tuning in English and also in ASEAN languages such as Indonesian, Thai and Vietnamese on our continued pre-trained Gemma-SEA-LION-v3-9B, a decoder model using the Gemma2 architecture, to create Gemma-SEA-LION-v3-9B-IT. For tokenisation, the model employs the default tokenizer used in Gemma-2-9B. The model has a context length of 8192.

• gemma-3-1b-it-GGUF↗

  ggml-org

  * [Gemma 3 Technical Report][g3-tech-report] * [Responsible Generative AI Toolkit][rai-toolkit] * [Gemma on Kaggle][kaggle-gemma] * [Gemma on Vertex Model Garden][vertex-mg-gemma3] Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. - **Input:** - Text string, such as a question, a prompt, or a document to be summarized - Images, normalized to 896 x 896 resolution and encoded to 256 tokens each - Total input context of 128K tokens for the 4B, 12B, and 27B sizes, and 32K tokens for the 1B size