전체 검색

AI 모델 449

• GLM-5.2-FP8-Uncensored-Colibri-Int4↗

  annelo

  This is a **Colibri-compatible int4 conversion** of zandenAI/GLM-5.2-FP8-Uncensored. It was created for JustVugg/colibri: a C inference engine that keeps the dense part in RAM and streams routed MoE experts from local storage. > This is an independent conversion, not an official Z.ai, NVIDIA, or Hugging Face release.

• multi_verse_model↗

  MTSAIR

  I'm an innovative concept, created through a cutting-edge training method. Picture me as a "learning bot" who's had a special upgrade. Just like how a chef perfects their recipes with new techniques, my creators have fine-tuned my "knowledge-absorption" process. I'm here to showcase the potential of this new approach, and I'm excited to test my abilities in a friendly, helpful manner. So, while I may be a product of experimentation, my purpose is to demonstrate the power of continuous learning and growth in the world of artificial intelligence.

• Olmo-3-32B-Think-MLX-6bit↗

  lmstudio-community

  _👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord_. **Model creator**: allenai **Original model**: Olmo-3-32B-Think **MLX quantization**: provided by LM Studio team using mlx_lm 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.

• SmolLM2-135M-GGUF↗

  prithivMLmods

  Ollama is a powerful tool that allows you to run machine learning models effortlessly. This guide will help you download, install, and run your own GGUF models in just a few minutes. To get started, download Ollama from https://ollama.com/download and install it on your Windows or Mac system. First, create a model file and name it appropriately. For example, you can name your model file `metallama`.

• distilbart-mnli-12-1↗

  valhalla

  distilbart-mnli is the distilled version of bart-large-mnli created using the **No Teacher Distillation** technique proposed for BART summarisation by Huggingface, here. If you want to train these models yourself, clone the distillbart-mnli repo and follow the steps below

• colSmol-256M↗

  vidore

  ColSmolVLM 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 SmolVLM 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 version is trained with the commit b983e40 of the Colpali repository. (main branch from the repo) 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.

• gemma-3n-E2B-it-litert-preview-GGUF↗

  unsloth

  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 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over 140 spoken languages. Gemma 3n models use selective parameter activation technology to reduce resource requirements. This technique allows the models to operate at an effective size of 2B and 4B parameters, which is lower than the total number of parameters they contain. For more information on Gemma 3n's efficient parameter management technology, see the Gemma 3n page. With instruction-tuned models, you need to use chat templates to process our inputs first. Then, you can pass it to the pipeline.

• DeepSeek-Prover-V2-7B↗

  DeepSeek

  We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSeek-V3 to decompose complex problems into a series of subgoals. The proofs of resolved subgoals are synthesized into a chain-of-thought process, combined with DeepSeek-V3's step-by-step reasoning, to create an initial cold start for reinforcement learning. This process enables us to integrate both informal and formal mathematical reasoning into a unified model. we introduce ProverBench, a benchmark dataset comprising 325 problems. Of these, 15 are formalized from number theory and algebra questions featured in the recent AIME competitions (AIME 24 and 25), offering authentic high-school competition-level challenges. The remaining 310 problems are drawn from curated textbook examples and educational tutorials, contributing a diverse and pedagogically grounded collection of formalized mathematical problems. This benchmark is designed to enable more comprehensive evaluation across both high-school competition problems and undergraduate-level mathematics. We release DeepSeek-Prover-V2 in two model sizes: 7B and 671B parameters. DeepSeek-Prover-V2-671B is trained on top of DeepSeek-V3-Base. DeepSeek-Prover-V2-7B is built upon DeepSeek-Prover-V1.5-Base and features an extended context length of up to 32K tokens.

• Huihui-Agents-A1-abliterated-GGUF↗

  huihui-ai

  This is an uncensored version of InternScience/Agents-A1 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. - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs. - **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.

• Huihui-Qwen3.8-27B-abliterated-GGUF↗

  Hirt556

  This is an uncensored version of Qwen/Qwen3.8-27B 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. The newly added **Huihui-Qwen3.8-27B-abliterated-Ternary** series come from prism-ml/Ternary-Bonsai-2-27B-gguf. Only layers **22 to 52 (0-based indexing)** have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. The size after conversion may differ from the original GGUF (Some of the weights are converted from PTQ1 to Q2_K or Q3_K.). This is just a test/validation. The ternary hybrid-attention kernels live in the PrismML-Eng/llama.cpp fork. **Stock llama.cpp will not run these files.**