# Fast Inference

ERNIE-4.5-0.3B-PT-bf16 is a version of the ERNIE series models developed by Baidu, with a parameter scale of 0.3B and trained using bf16 precision.

This is a model based on the Hugging Face Transformers library, optimized using Unsloth. Specific functionalities and use cases require further information.

This is a model based on the 🤗 transformers library, optimized using unsloth technology. Specific functions and uses require further information.

A 3B parameter instruction fine-tuned model based on Qwen2.5 architecture, optimized for training speed using Unsloth and Huggingface TRL library

This model is a PyTorch-based image-to-image transformation model, integrated and pushed to the Hub via PytorchModelHubMixin.

A bird sound classification model trained on wav2vec2-base, capable of identifying 21 bird species from the Vedanthangal Bird Sanctuary in India

Lite-Whisper is a compressed version of OpenAI Whisper, utilizing LiteASR technology to significantly reduce model size while maintaining high accuracy.

SmolLumi-8B-Instruct is an 8B-parameter Alpaca model trained using Unsloth and Huggingface TRL library, specializing in text generation inference tasks.

Stable Diffusion is a text-to-image diffusion model capable of generating high-quality images from text descriptions.

Groq-optimized version based on Llama-3-8B, supporting tool usage and function call capabilities

A vision-language model trained on the MetaCLIP-400M dataset, supporting zero-shot image classification tasks

This is a DistilBERT model fine-tuned on the SST-2 English dataset using AutoTrain for text classification tasks.

4-bit quantized version based on Meta-Llama-3.1-8B-Instruct, efficiently trained using Unsloth and TRL libraries

A text classification model based on PyTorch, which can be used for text classification-related tasks

Quantized version of FLUX.1-schnell, a text-to-image diffusion model supporting multiple quantization precision options

FLUX.1-schnell is a text-to-image generation model based on the GGUF format, suitable for image generation tasks.

LinFusion is a text-to-image generation model based on the Diffusers library, supporting the creation of high-quality images from text descriptions.

A 4-bit quantized version based on Meta-Llama-3.1-8B-Instruct, trained using Unsloth and Huggingface TRL libraries, achieving 2x speed improvement.

StableMaterials is a diffusion model-based physically based rendering (PBR) material generation tool capable of generating high-resolution, tileable material maps from text or image prompts.

This is an unconditional image generation diffusion model based on PyTorch and Diffusers library, specifically designed to generate adorable butterfly images.

A Turkish-English bilingual model fine-tuned from unsloth/llama-3-8b-bnb-4bit, optimized for training speed using Unsloth

A monocular normal estimation model fine-tuned using latent consistency distillation for predicting surface normal maps from single images

A text generation model fine-tuned based on unsloth/llama-3-8b-bnb-4bit, trained using Unsloth and TRL libraries with 2x speed improvement

This is a text-to-image model based on stable diffusion technology, capable of generating high-quality images from input text descriptions.

The Stable Diffusion Model is a text-to-image generation model capable of producing high-quality images based on textual descriptions.

A monocular depth estimation model fine-tuned using latent consistency distillation for generating depth maps from single images

A universal named entity recognition model specifically designed for Italian, utilizing zero-shot learning to identify a wide range of entity types without the need for training on specific entities.

Distil-Whisper is a distilled version of the Whisper model, 6x faster with 49% smaller size, achieving near 1% WER on out-of-distribution evaluation sets.

A text classification model fine-tuned based on bert-tiny, demonstrating good precision and accuracy on the evaluation set

A distilled consistency adapter designed for segmind/SSD-1B, reducing inference steps to just 2-8 steps

This is an unconditional image generation model based on diffusion models, specifically designed to generate adorable butterfly images.

The Stable Diffusion Model is a text-to-image diffusion model capable of generating high-quality images based on textual descriptions.

A text-to-image generation model based on diffusion models, capable of producing high-quality images from textual descriptions.

A small text-to-image generation model distilled from the Realistic_Vision_V4.0 model on a subset of the LAION-art-EN-improved-captions dataset

The Stable Diffusion Model is a text-to-image generation model capable of producing high-quality images based on textual descriptions.

A text-to-image generation model based on stable diffusion technology, capable of producing high-quality images from textual descriptions.

A text-to-image generation model based on stable diffusion technology, capable of producing high-quality images from textual descriptions.

RWKV is a large language model combining the advantages of RNN and Transformer, supporting efficient training and fast inference with unlimited context length processing capability.

A vision model for image classification, capable of recognizing various common objects and scenes.

A compact ResNet18 model trained on the CIFAR-10 dataset, achieving a test accuracy of 94.98%.