The Ming-flash-omni preview version is a multimodal large model built on the Ling-Flash-2.0 sparse mixture of experts (MoE) architecture, with a total of 100B parameters and only 6B parameters activated per token. This model is a comprehensive upgrade based on Ming-Omni, showing significant improvements in multimodal understanding and generation, especially in speech recognition, image generation, and segmentation editing.

MultimodalDiffusersEnglish

This is a large language model with 6B parameters based on the Qwen3 architecture, specifically fine-tuned for horror themes. It can generate dark and horror-style texts and performs well in logical reasoning tasks.

Natural Language ProcessingGgufMultiple Languages

This is a 6B-parameter Mixture of Experts model based on the GPT-OSS architecture. After pruning optimization, only 7 experts are retained, and it is the GGUF version using the Q4_K_M quantization format. This model focuses on efficient inference and text generation tasks, achieving better computational efficiency through pruning and quantization techniques.

Natural Language ProcessingGgufMultiple Languages

This is a specialized mixture of experts model with a scale of 6B parameters based on the GPT architecture. After pruning optimization, only 7 experts are retained, and it is converted into a quantized version in the GGUF format. The model uses Q8_0 quantization, significantly reducing memory usage and computational requirements while maintaining performance.

Natural Language ProcessingGgufMultiple Languages

A repository containing 44 Mixture of Experts (MOE) quantized models, suitable for coding tasks in multiple programming languages, with parameter scales ranging from 6B to 60B.

Natural Language ProcessingGgufMultiple Languages

InternVideo2 is a multimodal video understanding model with 6B parameters, focusing on video content analysis and comprehension tasks.

MultimodalSafetensors

The world's first 6B-parameter Llama-3 base model, an untrained version derived from Meta-Llama-3-8B using downgrade loop technology

Natural Language ProcessingTransformersEnglish

Yi 6B is a large language model developed by 01-ai, with 6 billion parameters, suitable for various text generation tasks.

Natural Language ProcessingGgufOther

DeciLM 6B-Instruct Model is an English language model specifically designed for short-format instruction following, trained using LoRA fine-tuning technology based on DeciLM 6B

Natural Language ProcessingTransformersEnglish

DeciLM 6B is a 5.7-billion-parameter decoder-only text generation model developed by Deci. It uses variable grouped query attention technology to achieve the best balance between performance and computational efficiency. This model has been instruction fine-tuned on the OpenOrca dataset, supports a context window of 4096 tokens, and can achieve a throughput up to 15 times that of Llama 2 7B.

Natural Language ProcessingTransformersEnglish

NSQL-6B is an autoregressive large language model base specifically designed for SQL generation tasks, pre-trained and fine-tuned based on Salesforce's CodeGen-Multi 6B model.

Natural Language ProcessingTransformers

GPT-JT is a large language model fine-tuned based on GPT-J (6B), utilizing UL2 training objectives, excelling in classification tasks

Natural Language ProcessingTransformersEnglish

VeriGen is a 6B-parameter model fine-tuned from CodeGen-multi-16B, specifically designed for generating Verilog hardware description language code.

Natural Language ProcessingTransformersOther

CodeGen is a series of autoregressive language models for program synthesis. CodeGen-Mono 6B is a 6B-parameter model further pre-trained on Python programming language datasets.

Natural Language ProcessingTransformers

InCoder 6B is a decoder - only Transformer model with 6 billion parameters, specifically trained for code generation tasks. This model supports left - to - right code generation as well as code insertion and filling functions, and is trained on codebases of 28 programming languages, mainly including Python and JavaScript.

Natural Language ProcessingTransformersOther

GPT-J 6B fine-tuned model for Python code generation, specialized in Python programming assistance

Natural Language ProcessingTransformersEnglish

GPT-J 6B is a Transformer model based on the GPT-3 architecture, featuring 6 billion parameters and supporting text generation tasks.

Natural Language ProcessingTransformers

This is a 6B-parameter Vietnamese causal language model based on GPT-J architecture, specifically trained for Vietnamese news content.

Natural Language ProcessingTransformersOther

This is the 8-bit quantized version of EleutherAI's GPT-J 6B parameter model, optimized for running and fine-tuning on limited GPU resources (e.g., Colab or 1080Ti).

Natural Language ProcessingTransformersEnglish

A sci-fi/fantasy-themed language model fine-tuned from GPT-J 6B, expanded with 20% multi-genre content

Natural Language ProcessingTransformersEnglish