Qwen3 is the latest generation of large language models in the Qwen series, offering a range of dense and mixture-of-experts (MoE) models. Based on extensive training, Qwen3 has achieved groundbreaking progress in reasoning, instruction following, agent capabilities, and multilingual support.

Natural Language ProcessingLlamafile

Qwen3-4B is the latest generation large language model in the Qwen series, featuring 4B parameters, supporting a 128k context window and over 100 languages, with outstanding performance in reasoning, instruction following, and agent capabilities.

Natural Language ProcessingLlamafile

Qwen3 is the latest generation of large language models in the Qwen series, offering a dense model with 0.6B parameters, achieving breakthrough progress in reasoning, instruction following, agent capabilities, and multilingual support.

Natural Language ProcessingLlamafile

Gemma 3 is a lightweight open-source model series launched by Google, built on Gemini technology, supporting multimodal input and text output.

MultimodalLlamafile

Gemma is a lightweight open model series launched by Google, built on the same research technology as Gemini. The llamafile version is packaged as an executable file by Mozilla for easy use on multiple platforms.

MultimodalLlamafile

This is a Whisper-small speech recognition model fine-tuned on French datasets, reducing the word error rate by 6.793 percentage points compared to the baseline model.

Audio ProcessingTransformersFrench

A YOLOv11-based object detection model for detecting swimming pools in satellite images.

Whisper-small speech recognition model fine-tuned on 35,141 Galician samples from Mozilla Common Voice dataset

Audio ProcessingTransformersOther

This is an automatic speech recognition (ASR) model fine-tuned from the openai/whisper-small model for Greek speech recognition tasks, trained on 3,620 Greek samples from the Mozilla Common Voice 17.0 dataset.

Audio ProcessingTransformersOther

DistilBART-CNN-12-6 is a distilled version of the BART model, specifically designed for text summarization tasks, featuring a smaller model size and higher inference efficiency.

Natural Language ProcessingTransformers

Russian automatic speech recognition (ASR) model optimized based on OpenAI Whisper Large V3 Turbo, fine-tuned using the Mozilla Common Voice 17 Russian dataset

Audio ProcessingTransformersOther

A vision-language model based on VIT image encoder and distilled GPT-2 text decoder for image caption generation tasks

MultimodalTransformers

This is a Bengali automatic speech recognition model based on the Whisper small architecture, fine-tuned on approximately 400 hours of Mozilla Common Voice dataset with a word error rate of 4.58%

Audio ProcessingTransformers

This model is a fine-tuned version of openai/whisper-tiny on the mozilla-foundation/common_voice_11_0 fr dataset, focusing on French speech recognition tasks.

Audio ProcessingTransformersFrench

Automatic speech recognition model fine-tuned on Mozilla Common Voice Portuguese dataset based on facebook/wav2vec2-xls-r-300m

Audio ProcessingTransformersOther

German ASR model trained on Mozilla Common Voice 6.1, German Wikipedia speech corpus, and m-ailabs corpus, achieving a word error rate of 7.24%

Audio ProcessingPytorchGerman

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - ia dataset for automatic speech recognition in Interlingua.

Audio ProcessingTransformersOther

This model is an automatic speech recognition model fine-tuned on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset for xls-r-dummy

Audio ProcessingTransformersOther

This is a small random robustness model based on the wav2vec2 architecture, fine-tuned on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset for automatic speech recognition tasks.

Audio ProcessingTransformersOther

This is a Portuguese automatic speech recognition model trained on the Mozilla Common Voice 7.0 dataset, supporting Portuguese speech-to-text tasks.

Audio ProcessingTransformersOther