Melta is a unique small language model developed based on the Discord bot Melta27. It has a cute, charming, and enthusiastic personality, and is specifically designed to generate original, unique, and cute text content.

Natural Language ProcessingTransformersFrench

This is a static quantized version based on mookiezi/Discord-Micae-Hermes-3-8B, a large language model specifically fine-tuned for Discord conversation data, supporting English text generation and conversation tasks.

Natural Language ProcessingTransformersEnglish

This is a collection of quantized versions based on the huehui/Discord-Micae-Hermes-3-3B-abliterated model, providing GGUF files of various quantization types and sizes. This model is a 3B parameter dialogue model trained on the Discord-OpenMicae dataset, supporting dialogue interactions in ChatML format.

Natural Language ProcessingTransformersEnglish

This is a statically quantized version based on the huehui/Discord-Micae-Hermes-3-3B-abliterated model, specifically optimized for text generation and conversation tasks. The model is trained using the mookiezi/Discord-OpenMicae dataset, supports English language processing, and offers multiple quantized versions to meet different hardware requirements.

Natural Language ProcessingTransformersEnglish

This is a quantized version based on the mookiezii/Discord-Hermes-3-8B model, providing GGUF model files in multiple quantization formats, suitable for dialogue AI application scenarios with different hardware environments and performance requirements.

Natural Language ProcessingTransformersEnglish

This is a statically quantized version of the mookiezii/Discord-Hermes-3-8B model, an 8B parameter language model specifically optimized for Discord conversation scenarios, offering multiple quantization formats to meet different hardware requirements.

Natural Language ProcessingTransformersEnglish

Discord-Hermes-3-8B is a large language model fine-tuned based on NousResearch/Hermes-3-Llama-3.1-8B, specifically optimized for conversation scenarios. Through training on a carefully curated Discord conversation dataset, it improves conversation ability and the quality of chat interaction.

Natural Language ProcessingTransformers

This is a 3B parameter language model based on the Hermes-3 architecture, specifically optimized for Discord chat scenarios. It provides GGUF format files in multiple quantization versions, suitable for local deployment and inference.

Natural Language ProcessingTransformers

OpenMed-NER-DNADetect-BioMed-109M is a model specifically designed for biomedical named entity recognition (NER). It is fine-tuned based on the BiomedELECTRA architecture and excels at accurately identifying key biomedical entities such as proteins, DNA, RNA, cell lines, and cell types from clinical texts and research papers. This model is trained on the JNLPBA dataset, featuring high accuracy and easy integration, and is suitable for scenarios such as drug discovery, clinical record analysis, and biomedical knowledge graph construction.

Natural Language ProcessingTransformersMultiple Languages

This is a biomedical named entity recognition model specifically designed for chemical entity recognition. It is trained on the BC4CHEMD dataset based on the BiomedBERT architecture and can accurately identify compounds and substances in biomedical literature, providing support for drug discovery and clinical research.

Natural Language ProcessingTransformersEnglish

A model specifically designed for chemical entity recognition, capable of accurately identifying and extracting relevant entities from biomedical texts, and has significant value in fields such as drug discovery and medical data analysis.

Natural Language ProcessingTransformersEnglish

This is a vision-language encoder model fine-tuned based on the SigLIP2 architecture, specifically designed for multi-class image classification of dental abnormalities and diseases. The model can detect six common dental problems, including dental calculus, dental caries, gingivitis, oral ulcers, tooth discoloration, and tooth loss.

Computer VisionTransformersEnglish

A DistilBERT-based shopping discount classification model that provides recommendations based on user queries

Natural Language ProcessingTransformersEnglish

PAE-LLaVa-7B is a foundation model Internet intelligent agent based on the PAE (Proposer-Agent-Evaluator) framework, focusing on autonomous skill discovery.

MultimodalSafetensors

This model is released under the MIT License, with specific details currently unknown.

Natural Language ProcessingTransformers

DrugAssist is a large language model specifically designed for molecular optimization, focusing on research in scientific fields such as drug discovery and molecular generation, and providing strong support for the application of AI in the scientific field.

Scientific ComputingTransformers

Precious3GPT is a multimodal, multi-omics, multi-species, multi-tissue life large language model designed for drug discovery and aging research

MultimodalTransformersMultiple Languages

A German-optimized large language model based on Meta Llama3-8B, continuously pre-trained on 65 billion German tokens, specifically optimized for German and supporting 32k long context

Natural Language ProcessingTransformersGerman

Llama3-German-8B-v0.1 is a German-optimized large language model based on Meta Llama3-8B. It has been continuously pre-trained on 65 billion high-quality German tokens and is specifically optimized for German tasks, showing excellent performance in German understanding and reasoning abilities.

Natural Language ProcessingTransformersGerman

This is an experimental German language model merging project that combines two excellent German models from OpenPipe and DiscoResearch, aiming to improve German generation quality

Natural Language ProcessingTransformersMultiple Languages