The BT4 model is the neural network model behind the LeelaChessZero engine, specifically designed for chess games. This model is based on the Transformer architecture and can predict the best next move based on historical moves, evaluate the game situation, and generate move probabilities.

Scientific ComputingTransformers

Devstral-Small-2507-AWQ is a quantized version derived from the mistralai/Devstral-Small-2507 model. It uses the AutoAWQ technology for 4-bit quantization and is optimized for efficient operation on the vLLM inference engine.

Natural Language ProcessingSafetensorsOther

Qwen3 30B A3B is a large language model that has undergone 8-bit quantization using the GPTQ method, suitable for efficient inference scenarios.

Natural Language ProcessingTransformers

Illustrious-XL-v2.0 is a foundational model for text-to-image generation, suitable for various image generation tasks.

Computer VisionGguf

A vision Transformer model based on the LeViT-128 architecture, fine-tuned for binary stroke detection tasks

Computer VisionTransformers

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on a binary stroke detection dataset for image classification tasks, achieving an evaluation accuracy of 92.22%.

Computer VisionTransformers

This is a quantized version of the text-to-image generation model based on Laxhar/noobai-XL-Vpred-1.0. It was quantized by btaskel, which can reduce the model size and improve the inference speed while maintaining good generation quality.

Computer VisionGguf

A scoring model based on Gemma-2b-it, trained with BT loss function, suitable for finding high-quality small scoring models for large language models

Natural Language ProcessingTransformers

BTLM-3B-8k-chat is a conversational version developed based on BTLM-3B-8K-base, optimized using DPO method, specifically designed for dialogue scenarios aligned with human preferences.

Natural Language ProcessingTransformersEnglish

Cappy is a pre-trained small-scale scorer designed to enhance the performance and efficiency of multi-task large language models (LLMs). The model takes instructions and candidate responses as input and outputs a score between 0 and 1, indicating the estimated correctness of the response relative to the instruction.

Natural Language ProcessingJax

BTLM-3B-8k-base is a 3-billion-parameter language model with an 8k context length, trained on the 627-billion-token SlimPajama dataset, delivering performance comparable to open-source 7-billion-parameter models.

Natural Language ProcessingTransformersEnglish

This is a voice conversion model based on RVC (Retrieval-Based Voice Conversion) technology, specifically trained for 1000 epochs to emulate the voice of BTS member Jungkook.

Audio ProcessingTransformers

A fine-tuned text summarization model based on barthez-orangesum-title, supporting keyword summarization for French texts

Natural Language ProcessingTransformers

A text summarization model fine-tuned based on barthez-orangesum-title, specializing in generating headline-style summaries

Natural Language ProcessingTransformers

A fine-tuned abstract generation model based on barthez-orangesum-title, trained on an unknown dataset, supporting French text summarization tasks.

Natural Language ProcessingTransformers

A Russian BTS fanfiction generation model fine-tuned from ruGPT-3, optimized for Russian fan communities

Natural Language ProcessingTransformers