This is a quantized version of TheDrummer's Snowpiercer-15B-v4 model, quantized using llama.cpp and imatrix technology. This version offers multiple quantization levels from BF16 to IQ2_S, meeting the needs of users with different hardware conditions and performance requirements. The model is calibrated and optimized using a specific dataset and supports the online repackaging function to improve performance on ARM and AVX hardware.

Natural Language ProcessingGguf

This project is a llama.cpp GGUF quantized version based on the Qwen3-VL-32B-Instruct model, offering various quantization types to meet different hardware and performance requirements. Quantization is performed using a specific dataset in combination with the imatrix option to ensure quantization quality. It supports online weight repackaging to improve the performance of ARM and AVX machines.

MultimodalGguf

Three document layout analysis models (nano, small, medium) based on the YOLOv11 architecture, fine-tuned on the DocLayNet dataset, can accurately detect 11 types of layout elements such as text, tables, and charts in documents, suitable for document understanding and information extraction tasks.

An action-chunking Transformer strategy model trained for blue or green building block classification, designed to control the SO-ARM100 robotic arm for block sorting and grasping tasks

Computer VisionSafetensors

This is the GGUF format conversion version of the mlabonne/gemma-3-1b-it-abliterated model, generated using the llama.cpp conversion tool. The model offers a variety of quantization options, suitable for different devices and scenarios, and is specially optimized for running efficiency on CPU and ARM devices.

Natural Language ProcessingTransformers

A CLIP-based fine-tuned model for LEGO brick image-text matching, specifically designed to recognize LEGO bricks and their descriptions.

MultimodalTransformersEnglish

Armenian text embedding model optimized based on multilingual-e5-base, supporting semantic search and cross-lingual understanding

Natural Language ProcessingTransformersMultiple Languages

A penetration testing assistant transformed from OpenHermes-2.5-Mistral-7B, optimized for the Kali Linux toolset, providing support for guided penetration testing and command automation.

Natural Language ProcessingTransformersEnglish

An object detection model based on YOLOv8, specifically designed for detecting handwritten text content

Western Armenian text-to-speech model developed by Meta, part of the Massively Multilingual Speech project

Audio ProcessingTransformers

A model designed for summarizing long Persian texts, supporting inputs of up to 8K tokens.

Natural Language ProcessingTransformersOther

A Persian text summarization model based on the Longformer attention mechanism, supporting input lengths of up to 8K tokens.

Natural Language ProcessingTransformersOther

This is a binary classification model trained using AutoTrain, specifically designed for wasp image classification tasks.

Computer VisionTransformers

This is a deep reinforcement learning model based on the TQC algorithm, specifically designed for the PandaPickAndPlace-v1 environment, used for robotic arm grasping and placing tasks.

Scientific ComputingStable-baselines3

Armenian automatic speech recognition model based on wav2vec2-xls-r-2b architecture, supporting hy/hye language

Audio ProcessingTransformersOther

This model is a Q&A model fine-tuned on the SQuAD2.0 and COVID-QA datasets based on the ALBERT-xxlarge-v2 architecture

Natural Language ProcessingTransformers

This is an automatic speech recognition model fine-tuned on the Armenian speech dataset based on facebook/wav2vec2-xls-r-300m

Audio ProcessingTransformers

This model is a fine-tuned version of DistilBERT on a COVID-19 Q&A dataset, specifically designed to answer questions related to COVID-19.

Natural Language ProcessingTransformers

An automatic speech recognition (ASR) model fine-tuned on Armenian language datasets based on facebook/wav2vec2-xls-r-300m, supporting Armenian speech-to-text tasks.

Audio ProcessingTransformersOther

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset, supporting Armenian speech recognition.

Audio ProcessingTransformers