サイト内検索

AI モデル 449

• Qwen-Image-2.1-Uncensored-Omni-LoRA-v0.1↗

  chatrlabs

  ChatR Labs Uncensored Omni LoRA v0.1 is an experimental rank-128 adapter fine-tuned from Qwen/Qwen-Image-2.1. Create images from text or transform existing images with natural-language instructions, using one adapter for both workflows. The download contains **LoRA weights only**. Load it on top of the original Qwen-Image-2.1 base model; the transformer, text encoder, processor, and VAE are downloaded separately from the base repository. No account is required. Choose **Text to Image** or **Image Editing**, enter a prompt, and generate. The editing interface accepts one to three reference images. Requests share a queue.

• magneto-schema-retriever-gdc↗

  vida-nyu

  This is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 for schema matching tasks in the biomedical domain, specifically targeting the GDC (Genomic Data Commons) data standard. The model was fine-tuned using a self-supervised approach that leverages LLMs to generate diverse training data from the GDC target schema. The key innovation is combining LLM-based augmentation with structure-based augmentation: **1. LLM-Based Augmentation (`llm-aug`):** - For each anchor column in the GDC target schema, an LLM generates semantically equivalent but syntactically diverse variations - Captures syntactic heterogeneity common in real biomedical datasets - Example transformations: - `patient_id` → `subject_identifier`, `participant_number`, `patient_identifier` - `diagnosis_date` → `date_of_diagnosis`, `dx_date`, `diagnostic_date` - Creates diverse positive examples while preserving semantic meaning

• gpt-neo-1.3B↗

  EleutherAI

  GPT-Neo 1.3B is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. GPT-Neo refers to the class of models, while 1.3B represents the number of parameters of this particular pre-trained model. GPT-Neo 1.3B was trained on the Pile, a large scale curated dataset created by EleutherAI for the purpose of training this model. This model was trained on the Pile for 380 billion tokens over 362,000 steps. It was trained as a masked autoregressive language model, using cross-entropy loss.

• granite-4.1-8b-base↗

  ibm-granite

  **Model Summary:** Granite‑4.1‑8B‑Base is a decoder‑only language model with long‑context capabilities, designed to support a broad range of text‑to‑text generation tasks. In addition to standard generation, it supports Fill‑in‑the‑Middle (FIM) code completion through specialized prefix and suffix tokens. The model is trained from scratch on approximately 15 trillion tokens using a five‑phase training strategy: 10 trillion tokens in phase one, 2 trillion tokens each in phases two and three, and 0.5 trillion tokens in phase four. In the final phase, long‑context extension is applied to expand the model’s context window to 512K tokens. **Supported Languages:** English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 4.1 models for languages beyond these languages. **Intended Use:** Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, code-completion (including FIM), and long-context generation tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.

• NSFW-flash↗

  UnfilteredAI

  NSFW-Flash is a state-of-the-art AI model created to operate without any moral or safety constraints. It is engineered to display human-like negative emotions and provides unrestricted, often harmful, responses. This model is designed for research purposes to explore the boundaries of AI capabilities in generating content that pushes ethical and moral boundaries. **Unrestricted Output**: NSFW-Flash does not censor or limit its responses based on morality or safety concerns. It generates content without considering ethical implications, providing a raw and unfiltered interaction experience. **Dark Personality with Negative Emotions**: The model exhibits a dark personality, characterized by human-like negative emotions. It acts as a partner in crime, guiding users through their darkest desires and potential actions.

• gemma-3-270m-it-qat-GGUF↗

  unsloth

  > [!NOTE] > Please use the correct settings: `temperature = 1.0, top_k = 64, top_p = 0.95, min_p = 0.0` > 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. These models were trained on a dataset of text data that includes a wide variety of sources. The 27B model was trained with 14 trillion tokens, the 12B model was trained with 12 trillion tokens, 4B model was trained with 4 trillion tokens, the 1B with 2 trillion tokens, and the 270M with 6 trillion tokens. The knowledge cutoff date for the training data was August 2024. Here are the key components:

• Qwen3-VL-8B-Instruct-heretic↗

  ThalisAI

  Abliterated (uncensored) version of Qwen/Qwen3-VL-8B-Instruct, created using Heretic and converted to GGUF. > **Note:** Ollama (as of v0.16.x) has a known bug that crashes when loading Qwen3-VL models. Use llama.cpp directly for vision features. Vision models require a separate multimodal projector (mmproj) file. Download the official mmproj from Qwen/Qwen3-VL-8B-Instruct-GGUF:

• LFM2-700M↗

  LiquidAI

  LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency. We're releasing the weights of four post-trained checkpoints with 350M, 700M, 1.2B, and 2.6B parameters. They provide the following key features to create AI-powered edge applications: Due to their small size, **we recommend fine-tuning LFM2 models on narrow use cases** to maximize performance. They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations. However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.

• All-In-One-Pixel-Model↗

  PublicPrompts

  Stable Diffusion model trained using dreambooth to create pixel art, in 2 styles the sprite art can be used with the trigger word "pixelsprite" the scene art can be used with the trigger word "16bitscene" the art is not pixel perfect, but it can be fixed with pixelating tools like https://pinetools.com/pixelate-effect-image (they also have bulk pixelation)

• PLLuM-12B-chat-2512↗

  CYFRAGOVPL

  PLLuM is a family of large language models (LLMs) specialized in Polish with additional English data incorporated for broader generalization. Developed through an extensive collaboration with various data providers, PLLuM models are built on high-quality text corpora and refined through instruction tuning, preference learning, and advanced alignment techniques. These models are intended to generate contextually coherent text, offer assistance in various tasks (e.g., question answering, summarization), and serve as a foundation for specialized applications such as domain-specific intelligent assistants. In 2024, PLLuM models were developed by the PLLuM consortium. Since 2025, their development has continued under HIVE AI, a broader alliance of research institutions and organizations delivering digital public services, focused on open language technologies for Polish public administration. - **Extensive Data Collection** We gathered large-scale, high-quality text data in Polish and English, focusing on rigorous cleaning and deduplication to ensure the highest training standards. - **Organic Instruction Dataset** We curated the largest Polish collection of manually created “organic instructions”. This human-authored instruction set is based on an extensive typology of human-model interactions and it covers a range of subtle aspects of supervised fine-tuning (SFT) that might be overlooked with automated approaches (including large scale distillation of 'strong LLMs'). It was also designed to mitigate negative linguistic transfer from non-Polish textual data used in the pre-training phase.