全站搜索

AI 模型 449

• Devstral-Small-2505-MLX-4bit↗

  lmstudio-community

  *👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord*. **Model creator:** mistralai **Original model**: Devstral-Small-2505 **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.

• gemma-3-4b-pt↗

  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 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 and 1B with 2 trillion tokens. Here are the key components: The combination of these diverse data sources is crucial for training a powerful multimodal model that can handle a wide variety of different tasks and data formats.

• vit-base-nsfw-detector↗

  hakl36

  This model is a fine-tuned version of vit-base-patch16-384 on around 25_000 images (drawings, photos...). It achieves the following results on the evaluation set: - Loss: 0.0937 - Accuracy: 0.9654 ** New [07/30] **: I created a new ViT model specifically to detect NSFW/SFW images for stable diffusion usage (read the disclaimer below for the reason): **AdamCodd/vit-nsfw-stable-diffusion**. **Disclaimer**: This model wasn't made with generative images in mind! There is no generated image in the dataset used here, and it performs significantly worse on generative images, which will require another ViT model specifically trained on generative images. Here are the model's actual scores for generative images to give you an idea: - Loss: 0.3682 (↑ 292.95%) - Accuracy: 0.8600 (↓ 10.91%) - F1: 0.8654 - AUC: 0.9376 (↓ 5.75%) - Precision: 0.8350 - Recall: 0.8980

• Smaug-34B-v0.1↗

  abacusai

  This model is a finetune of jondurbin's excellent bagel model. This model has not utilised any form of merging. We created Smaug-34B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228. We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions.

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

  Fhjdjdbxhshsh

  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-Underdog-Saluki** series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-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. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF weights of Swift-1.5 and ConwayResearch/Underdog-Saluki-27B-1.0.

• h2ovl-mississippi-800m↗

  h2oai

  The H2OVL-Mississippi-800M is a compact yet powerful vision-language model from H2O.ai, featuring 0.8 billion parameters. Despite its small size, it delivers state-of-the-art performance in text recognition, excelling in the Text Recognition segment of OCRBench and outperforming much larger models in this domain. Built upon the robust architecture of our H2O-Danube language models, the Mississippi-800M extends their capabilities by seamlessly integrating vision and language tasks. - 0.8 Billion Parameters: Balance between performance and efficiency, making it suitable for OCR and document processing. - Trained on 19 million image-text pairs, with a focus on OCR, document comprehension, and chart, figure, and table interpretation, the model is optimized for superior OCR performance. This guide demonstrates how to create prompts for extracting information and converting it into structured JSON outputs. It starts with basic examples and progresses to more complex JSON structures, including handling data from images of tables and charts. The objective is to help users design effective prompts that can be used in various applications, such as natural language processing, chatbots, or data extraction from visual inputs.

• Llama-3.1-Nemotron-Nano-4B-v1.1↗

  NVIDIA

  Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model (LLM) which is a derivative of nvidia/Llama-3.1-Minitron-4B-Width-Base, which is created from Llama 3.1 8B using our LLM compression technique and offers improvements in model accuracy and efficiency. It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling. Llama-3.1-Nemotron-Nano-4B-v1.1 is a model which offers a great tradeoff between model accuracy and efficiency. The model fits on a single RTX GPU and can be used locally. The model supports a context length of 128K. This model underwent a multi-phase post-training process to enhance both its reasoning and non-reasoning capabilities. This includes a supervised fine-tuning stage for Math, Code, Reasoning, and Tool Calling as well as multiple reinforcement learning (RL) stages using Reward-aware Preference Optimization (RPO) algorithms for both chat and instruction-following. The final model checkpoint is obtained after merging the final SFT and RPO checkpoints

• chinese-hubert-base↗

  TencentGameMate

  Pretrained on 10k hours WenetSpeech L subset. More details in TencentGameMate/chinese_speech_pretrain 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.

• blt-1b-hf↗

  itazap

  **BLT (Byte Latent Transformer)** is a tokenizer-free transformer architecture that operates directly on raw byte sequences. Instead of processing text token by token, BLT dynamically groups bytes into **entropy-based patches**, enabling more efficient and scalable processing for byte-level tasks. Key components: - **Local Encoder → Latent Transformer → Local Decoder** architecture. - **Entropy-based patcher (BltPatcher)**: scans byte streams and creates patches when entropy thresholds are met. - **Hash n-gram embeddings**: maintain contextual information over neighboring bytes. BLT achieves competitive performance compared to traditional token-based transformers, supporting multilingual, noisy, or mixed-script input.

• openai-gpt↗

  openai-community

  - Model Details - How To Get Started With the Model - Uses - Risks, Limitations and Biases - Training - Evaluation - Environmental Impact - Technical Specifications - Citation Information - Model Card Authors **Model Description:** `openai-gpt` (a.k.a. "GPT-1") is the first transformer-based language model created and released by OpenAI. The model is a causal (unidirectional) transformer pre-trained using language modeling on a large corpus with long range dependencies. - **Developed by:** Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever. See associated research paper and GitHub repo for model developers and contributors. - **Model Type:** Transformer-based language model - **Language(s):** English - **License:** MIT License - **Related Models:** GPT2, GPT2-Medium, GPT2-Large and GPT2-XL - **Resources for more information:** - Research Paper - OpenAI Blog Post - GitHub Repo - Test the full generation capabilities here: https://transformer.huggingface.co/doc/gpt