This is a cross-encoder model fine-tuned on the LangCache sentence pair dataset using the sentence-transformers library, based on the Alibaba-NLP/gte-reranker-modernbert-base model. It is specifically designed to calculate the semantic similarity score between text pairs, aiming to provide efficient text matching and reordering capabilities for the LangCache semantic cache system.

Natural Language ProcessingSentence-transformersEnglish

Rnj-1-instruct is an 8-billion-parameter open-weight dense model trained from scratch by Essential AI. It is optimized for code, STEM fields, agent capabilities, and tool invocation. It performs excellently in multiple programming languages and also demonstrates strong capabilities in mathematics and science, comparable to the most advanced open-weight models.

Natural Language ProcessingTransformers

This is a hybrid - language AI model specifically designed for call record analysis, capable of handling call transcription content in Hindi, English, and mixed Hindi - English. The model is fine - tuned based on Qwen2.5 - 1.5B - Instruct and has powerful multilingual understanding and information extraction capabilities.

Natural Language ProcessingTransformersMultiple Languages

This model is a quantized (Int8 / Q8) version of mixedbread-ai/mxbai-edge-colbert-v0-17m, exported specifically for use with transformers.js. It includes a custom projection layer required for the 48-dimensional ColBERT architecture, aiming to provide efficient vector retrieval capabilities.

Natural Language ProcessingTransformers

Strawberry_Smoothie-TEST is a hybrid model obtained by merging three 12B parameter models using the mergekit tool. It combines the advantages of Unity-12B, Chaos-Unknown-12b, and Smoothie-12B-Model_Stock, aiming to provide better text generation and dialogue capabilities.

Natural Language ProcessingTransformers

Profluent - E1 is a faithful implementation of the E1 model by Profluent Bio, released by Synthyra. It is a pre-trained language model focused on protein sequence processing, integrating Hugging Face AutoModel compatibility and providing efficient embedding capabilities, aiming to simplify protein sequence analysis and representation learning in bioinformatics tasks.

Scientific ComputingTransformers

Rnj-1 is a series of 8 billion parameter, open-weight dense models trained from scratch by Essential AI. This model is optimized for the code and STEM fields, excelling in programming, mathematical reasoning, agent tasks, and tool invocation, with capabilities comparable to the most advanced open-weight models.

Natural Language ProcessingTransformers

Qwen3-VL-2B-Instruct is the most powerful vision-language model in the Qwen series. It has excellent text understanding and generation capabilities, in-depth visual perception and reasoning abilities, long context support, and strong spatial and video dynamic understanding abilities. This model uses a 2B parameter scale, supports instruction interaction, and is suitable for multimodal AI applications.

MultimodalTransformers

This project performs MXFP4_MOE quantization on the Qwen3-VL-235B-A22B-Thinking model, aiming to provide more efficient image text-to-text conversion capabilities. This version is from unloth, and the context size has been extended from 256k to 1M. The model's performance in different scenarios is optimized through specific quantization techniques.

MultimodalGguf

LFM2-VL-3B is a multimodal vision-language model developed by Liquid AI, built on the LFM2 backbone architecture. It has powerful visual understanding and reasoning capabilities, especially excelling in fine-grained perception tasks. This model can efficiently process text and image inputs and supports native image processing with a resolution of up to 512×512.

MultimodalTransformersMultiple Languages

Apriel-1.5-15b-Thinker is a multimodal reasoning model developed by the ServiceNow SLAM Lab, with a parameter scale of 15 billion. It has powerful text and image understanding and reasoning capabilities, adopting a chained reasoning mode of 'think-answer', aiming to achieve performance comparable to large models with a smaller model scale.

MultimodalTransformers

lans_v1 - lora is a text-to-image conversion model trained using the AI Toolkit by Ostris based on the Qwen/Qwen-Image model. It is optimized using LoRA technology and has good image generation capabilities.

MultimodalDiffusers

This is a LoRA adapter trained based on the Wan2.1-T2V-14B model, specifically designed for text-to-video conversion tasks and providing enhanced capabilities for image generation. This model is trained using the AI Toolkit and requires a specific trigger word 'diddly' to activate image generation.

MultimodalDiffusers

qwen_edit_photo_restore_v1-lora is a LoRA adapter trained based on the Qwen-Image-Edit model, specifically designed for image editing and restoration tasks. This model is trained using the AI Toolkit by Ostris, supports multiple mainstream AI platforms, and provides high-quality image processing capabilities.

MultimodalDiffusers

Granite-4.0-Micro is a long-context instruction model developed by IBM with 3 billion parameters, fine-tuned from Granite-4.0-Micro-Base. This model uses an open-source instruction dataset and an internal synthetic dataset, and has enhanced instruction-following and tool invocation capabilities. It supports multilingual tasks and can serve as a base model for AI assistants in various fields.

Natural Language ProcessingTransformers

GLM-4.6 is a new-generation text generation model launched by Zhipu AI. Compared with GLM-4.5, it has achieved significant improvements in context processing, encoding performance, reasoning ability, etc. It supports a context length of 200K and has stronger agent capabilities and refined writing abilities.

Natural Language ProcessingTransformersMultiple Languages

Llama-3.1-8B-onnx-ryzenai-npu is an optimized version developed by AMD based on Meta's Llama-3.1-8B model, specifically optimized for deployment on the AMD Ryzen AI NPU. Through Quark quantization, OGA model builder, and NPU-specific post-processing technology, this model significantly improves the inference efficiency on AMD hardware while maintaining high-quality text generation capabilities.

Natural Language ProcessingOnnxEnglish

NeuTTS Air is the world's first ultra-realistic, edge-side text-to-speech (TTS) language model with instant voice cloning capabilities. Built on a large language model backbone with 0.5B parameters, it brings natural voice, real-time performance, built-in security, and speaker cloning capabilities to local devices.

Audio ProcessingGguf

NeuTTS Air is the world's first ultra-realistic on-device text-to-speech model with instant voice cloning capabilities. It is built on a large language model backbone with 0.5B parameters and can achieve natural speech generation, real-time performance, and speaker cloning on local devices.

Audio ProcessingGguf

This project is the A3B quantized version of Alibaba's Tongyi In-depth Research 30B model. It aims to reduce the model deployment cost through quantization technology and make knowledge accessible to everyone. This model is optimized based on a large language model with a scale of 30B parameters, maintaining the strong capabilities of the original model while improving the inference efficiency.

Natural Language ProcessingGguf