This is an experimental pre-trained model based on RouWei-0.8, adopting a 16-channel latent space architecture and using a Flux autoencoder. The model aims to achieve finer image details at a lower computational cost while retaining the knowledge and performance of the original model.

Computer VisionDiffusersEnglish

MiniMax-M2 is a Mixture of Experts model designed for efficient coding and agent workflows. It has a total of 230 billion parameters and 10 billion active parameters. This model performs excellently in coding and agent tasks, and features low latency, low cost, and high throughput, effectively improving work efficiency.

Natural Language ProcessingTransformers

Qwen3-Nemotron-32B-RLBFF is a large language model fine-tuned based on Qwen/Qwen3-32B. The quality of the model's generated responses in the default thinking mode has been significantly improved through reinforcement learning feedback technology. This model performs excellently in multiple benchmark tests while maintaining low inference costs.

Natural Language ProcessingTransformersEnglish

LLaVA-OneVision-1.5 is a series of fully open-source large multimodal models that achieve advanced performance at a lower cost by training on native resolution images. This model demonstrates excellent performance in multiple multimodal benchmark tests, surpassing competitors such as Qwen2.5-VL.

MultimodalTransformers

MobileLLM-R1 is an efficient inference model in the MobileLLM series, specifically optimized for mathematics, programming, and scientific problems. It achieves higher accuracy with a smaller parameter scale, featuring low training cost and high efficiency.

Natural Language ProcessingTransformersEnglish

PARD is a high-performance speculative decoding method that can convert autoregressive draft models into parallel draft models at low cost, significantly improving the inference speed of large language models and reducing deployment complexity and adaptation costs.

Natural Language ProcessingTransformers

Kokoro is an open-source text-to-speech model with 82 million parameters. It uses a lightweight architecture but can provide quality comparable to large models. It has the advantages of high speed and low cost. It uses the Apache license and is suitable for production environments and personal projects.

Audio ProcessingMlxEnglish

The Holo1-7B GGUF model is part of the Surfer-H system and is suitable for multimodal tasks such as visual document retrieval. It is particularly good at web page interaction and network monitoring, and can achieve high accuracy at a low cost.

MultimodalTransformersEnglish

PARD is a high-performance speculative decoding method that can convert autoregressive draft models into parallel draft models at low cost, significantly accelerating the inference of large language models.

Natural Language ProcessingTransformers

xGen-small is an enterprise-grade compact language model that achieves long-context performance with predictable low costs through domain-focused data curation, scalable pre-training, length extension, and reinforcement learning fine-tuning.

Natural Language ProcessingTransformersEnglish

Fathom-R1-14B is a project based on the R1-distilled-14B model, achieving o4-mini level mathematical reasoning ability under a 16K context with a low training cost of $499.

Natural Language ProcessingTransformers

InternLM3-8B-Instruct is an 8-billion-parameter instruction model developed by Shanghai AI Laboratory, designed for general-purpose use and advanced reasoning, featuring high efficiency and low cost.

Natural Language ProcessingSafetensors

CogVideoX is the open-source version of the video generation model from Qingying. The 2B version is an entry-level model that balances compatibility with low operational and development costs.

MultimodalDiffusersEnglish

CogVideoX is an open-source video generation model originating from Qingying. The 2B version is an entry-level model, balancing compatibility with low operational and development costs.

MultimodalDiffusersEnglish

JetMoE-8B is an efficient open-source large language model that surpasses LLaMA2-7B performance with a low training cost of $100,000, activating only 2.2 billion parameters during inference

Natural Language ProcessingTransformers

JetMoE-8B is an efficient open-source large language model that achieves performance comparable to LLaMA2-7B with a training cost of under $100,000, specifically designed for low-resource environments.

Natural Language ProcessingTransformers

Pixart-α is an efficient text-to-image generation model based on Transformer architecture, capable of generating high-quality 1024-pixel images at extremely low training costs

Computer VisionDiffusers

ELECTRA is a self-supervised language representation learning method through discriminative pre-training, achieving efficient training with lower computational costs.

Natural Language ProcessingJaxEnglish

FrugalScore is an efficient natural language generation evaluation metric that transfers the performance of large teacher models to small student models through knowledge distillation technology, achieving high-quality text evaluation at low cost.

Natural Language ProcessingTransformers

An efficient Arabic language model based on Funnel Transformer and ELECTRA objective, with low computational cost and superior performance

Natural Language ProcessingTransformers