# Multi-scenario Adaptation

Quantized version of Devstral-Small-2505, offering multiple precision options to adapt to different hardware requirements

Ultravox v0.5 is an audio-to-text model optimized from the Llama-3 2.1B architecture, focusing on efficient speech transcription tasks.

AM-Thinking-v1 is a text generation model based on the GGUF format, suitable for various natural language processing tasks.

Llamacpp quantized version based on andrewzh's Absolute_Zero_Reasoner-Coder-7b model, supporting multiple quantization levels, suitable for reasoning and code generation tasks.

DeepHermes-ToolCalling-Specialist-Atropos is a text generation model focused on tool calling, designed to achieve efficient task execution through natural language processing technology.

Remnant-GLM4-32B is a 32B-parameter large language model based on the GLM4 architecture, supporting role-playing and conversational interactions, particularly suitable for salamander-related applications.

This is a Bert model optimized for German, focusing on text classification tasks in the quality domain.

GLM-4-9B-0414-abliterated is a large language model with 9B parameters based on the GLM architecture, suitable for text generation tasks.

TRELLIS Text XL is a large-scale text-conditioned 3D generation model that can generate corresponding 3D content based on the input text.

TRELLIS Text Large is a large-scale text-to-3D generation model that enables scalable and diverse 3D content generation based on a structured 3D latent space.

GGUF quantized version of DeepSeek-R1-Distill-Llama-70B-abliterated, suitable for local inference, offering multiple quantization options to meet different hardware requirements.

ViTPose is a vision Transformer-based human pose estimation model that achieves an outstanding performance of 81.1 AP on the MS COCO keypoint detection benchmark with a simple design.

A vision Transformer-based human pose estimation model achieving an outstanding performance of 81.1 AP on the MS COCO keypoint test set

An 8B-parameter summary generation model optimized based on Llama3 architecture, offering multiple quantization versions

SAM2 model based on the HieraDet image encoder, focusing on image feature extraction tasks.

SAM2 model weights based on HieraDet image encoder, focused on image feature extraction tasks

ONNX-format automatic speech recognition model based on the Moonshine base model, supporting efficient inference

A speech emotion recognition model based on WavLM-Large, supporting English speech emotion classification.

A LoRA model customized based on the FLUX.1-dev foundation model, specializing in generating realistic-style portraits of Jenna Ortega.

Pathumma Whisper Large V3 is a Thai automatic speech recognition model based on the OpenAI Whisper architecture, supporting Thai and English speech transcription tasks.

Allegro is an open-source high-quality text-to-video generation model capable of producing 6-second detailed videos at 720x1280 resolution and 15 FPS.

A Chinese speech recognition model fine-tuned based on whisper-large-v3-turbo, showing significant performance improvements in multiple Chinese speech recognition benchmarks

PGTFormer is an image-to-image transformation model based on PyTorch, integrated and pushed to Hugging Face Hub via PytorchModelHubMixin.

Reverb Speaker Diarization V2 is a speaker diarization model based on pyannote-audio, outperforming the baseline pyannote3.0 model on multiple test sets.

This model is used to convert image content into textual descriptions and is suitable for non-commercial purposes.

add-detail-xl is a detail adjustment model for SDXL. It can increase or decrease image details by adjusting the weight, bringing more flexibility to image generation.

This is a PyTorch-based text classification model suitable for various text classification tasks.

This model can convert input images into descriptive text, suitable for image understanding tasks in various scenarios.

A face detection model based on the CreativeML-OpenRAIL-M license, supporting the English language, primarily used for object detection tasks.

This model is an image-to-text model based on the Apache-2.0 license, capable of converting image content into textual descriptions.

A prompt optimization model fine-tuned using the QLORA method, specifically designed to enhance the clarity and effectiveness of text prompts.

The Chinese HuBERT base model is a pre-trained model for text-to-speech tasks, supporting Chinese speech processing.

Chinese pre-trained model based on RoBERTa architecture, supporting text-to-speech tasks

This model can convert input images into descriptive text, suitable for various image content understanding tasks across multiple scenarios.

OpenBuddy is an open-source multilingual chatbot that supports communication in multiple languages.

A Chinese speech recognition model fine-tuned based on distilwhisper-large-v2, with a speed 5.8 times faster than whisper-large-v2 and 51% fewer parameters

This is a distilled version of the Whisper-Large-V3 French model, optimized for inference speed and memory usage by reducing the number of decoder layers while maintaining good performance.

A French automatic speech recognition model fine-tuned based on OpenAI Whisper-large-v3, supporting case sensitivity, punctuation, and number prediction

OrionStar Yi 34B Chat Llama is a large language model based on the Yi 34B architecture, focusing on Chinese dialogue tasks.

Noromaid-20b-v0.1.1 is a large language model suitable for role-playing, emotional role-playing, and general scenarios, jointly developed by IkariDev and Undi.