Ouro-2.6B is a recurrent language model with 2.6 billion parameters. It achieves excellent parameter efficiency through iterative shared-weight computation and reaches the performance level of a standard Transformer model with 3 - 4 billion parameters using only 2.6 billion parameters.

Natural Language ProcessingTransformers

Ouro-1.4B is a recurrent language model developed by ByteDance with 1.4 billion parameters. It achieves excellent parameter efficiency through iterative shared-weight computation, reaching the performance level of a standard Transformer model with 3 - 4 billion parameters using only 1.4 billion parameters.

Natural Language ProcessingTransformers

The Artificial Hippocampus Network (AHN) is an innovative long-context modeling method that combines the accuracy of lossless memory with the efficiency of compressed memory by converting lossless memory into a fixed-size compressed representation. This model can effectively handle long sequences with a fixed computational cost and is suitable for various RNN-like architectures.

Natural Language ProcessingTransformersEnglish

AHN is an innovative neural network architecture for efficient long context modeling. By converting lossless memory into a fixed-size compressed representation, it combines the advantages of Transformer and RNN, achieving efficient computation and accurate prediction in long sequence processing.

Natural Language ProcessingTransformersEnglish

This is a lightweight version of the ByteDance Seed-OSS-36B-Instruct model quantized to 4 bits using DWQ. It is distilled from the BF16 teacher model using mlx-lm 0.27.1 and supports Chinese-English bilingual text generation tasks.

Natural Language ProcessingMlxMultiple Languages

This is a Japanese pre - trained language model based on the Mistral 300M architecture. It is trained using the Wikipedia and cc100 datasets, and the byte - fallback technique in the SentencePiece tokenizer is adopted to suppress the generation of unknown words.

Natural Language ProcessingTransformers

This is a static quantization version of the ByteDance-Seed/Seed-OSS-36B-Instruct model, providing GGUF format files with multiple quantization levels to help developers use the model more efficiently under different hardware configurations.

Natural Language ProcessingGguf

Seed-OSS-36B-Instruct is a large language model developed by ByteDance-Seed, with 36 billion parameters and released under the Apache 2.0 open-source license. This model is built on the transformers library, supports vllm and mlx technology optimization, and has undergone 8-bit quantization specifically for Apple Silicon chips, providing efficient text generation capabilities.

Natural Language ProcessingTransformers

Seed-OSS-36B-Instruct is a large language model with 36 billion parameters developed by the ByteDance Seed team. It is built on the Transformer architecture, processed with MLX quantization, and specifically optimized for Apple Silicon chips. It can run efficiently in LM Studio.

Natural Language ProcessingTransformers

This is the quantized version of ByteDance-Seed/cudaLLM-8B, which is committed to making large language models easier to deploy and use through model compression technology, realizing the concept of 'Let knowledge be used by everyone'.

Natural Language ProcessingGguf

This is a quantized version of the Seed-OSS-36B-Instruct model from ByteDance-Seed. It undergoes multi-precision quantization processing using the llama.cpp tool, offering more than 20 quantization options from BF16 to IQ2_XXS, aiming to enhance the model's operating efficiency and performance on different hardware.

Natural Language ProcessingGguf

Seed-OSS is an open-source large language model series developed by the ByteDance Seed team. It has powerful long context processing, reasoning, and agent interaction capabilities. Trained with only 12T tokens, it performs excellently in multiple public benchmark tests and supports native long context processing of up to 512K.

Natural Language ProcessingTransformers

Seed OSS 36B Instruct is a large-scale language model developed by ByteDance, with 36 billion parameters, specifically optimized for instruction-following tasks. It is built on the llama.cpp framework and supports efficient text generation capabilities.

Natural Language ProcessingGguf

Seed-OSS-36B-Instruct is a large language model with 36 billion parameters developed by ByteDance and is open-sourced under the Apache-2.0 license. This model is specifically optimized for instruction following tasks, supporting text generation and dialogue functions, and has powerful understanding and generation capabilities.

Natural Language ProcessingGguf

Seed-OSS-36B-Instruct is a text generation model developed by ByteDance. It is based on a large language model architecture with a 36B parameter scale and is specifically optimized for instruction-following tasks. This model supports both English and Chinese and uses the Apache-2.0 open-source license. It can be efficiently deployed through the vllm and mlx inference frameworks.

Natural Language ProcessingMlxMultiple Languages

Seed-OSS-36B-Instruct is a large-scale language model developed by ByteDance, with 36 billion parameters, focusing on text generation tasks. This model is implemented based on the MLX framework, supports both English and Chinese, and has powerful instruction following and text generation capabilities.

Natural Language ProcessingMlxMultiple Languages

Seed-OSS-36B-Instruct is a large language model with 36 billion parameters developed by ByteDance. It is optimized based on the MLX framework and focuses on text generation tasks. This model supports both English and Chinese, and uses the Apache 2.0 open-source license. It has powerful instruction-following and content generation capabilities.

Natural Language ProcessingMlxMultiple Languages

Seed-OSS-36B-Instruct-AWQ is a quantized version of the 36B parameter large language model developed by the ByteDance Seed team. It has powerful long context processing capabilities, reasoning capabilities, and agent functions, and supports a context length of up to 512K and flexible thinking budget control.

Natural Language ProcessingTransformersMultiple Languages

Seed-OSS is an open-source large language model series developed by the ByteDance Seed team. It has powerful long context processing, reasoning, agent interaction capabilities, and general performance. This model was trained with only 12T tokens and performed excellently in multiple public benchmark tests.

Natural Language ProcessingTransformersMultiple Languages

cudaLLM-8B is a professional language model developed by ByteDance Seed, specifically designed to generate high-performance and syntactically correct CUDA kernel code. Built on the Qwen3-8B base model, it is trained through two stages of supervised fine-tuning and reinforcement learning, enabling it to assist developers in writing efficient GPU parallel programming code.

Natural Language ProcessingTransformersEnglish