InternVL3.5-4B is a medium-scale version in the open-source multimodal model series, achieving significant progress in generality, reasoning ability, and reasoning efficiency, and supporting new capabilities such as GUI interaction. The model adopts a cascaded reinforcement learning framework and visual resolution router technology to achieve efficient multimodal understanding and reasoning.

MultimodalTransformersOther

InternVL3_5-38B is a member of the open-source multimodal model InternVL3.5 series, which has made significant progress in versatility, reasoning ability, and reasoning efficiency. It supports multiple languages and can be applied to image-text-to-text tasks. It uses a cascaded reinforcement learning framework and visual resolution router technology to optimize performance.

MultimodalTransformersOther

InternVL3.5-4B is a medium-scale version of the open-source multimodal model series, containing 470 million parameters. It adopts an advanced cascaded reinforcement learning framework and visual resolution router technology, significantly improving the multimodal reasoning ability and efficiency.

MultimodalTransformersOther

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 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

ERNIE-4.5-21B-A3B is a large language model developed by Baidu. It has been optimized with 4-bit quantization by the LM Studio team using the MLX framework, specifically optimized for Apple chips. This model has 21 billion parameters, supports Chinese and English, and uses the Apache-2.0 open-source license.

Natural Language ProcessingTransformersMultiple Languages

OpenF5 TTS is an open-source text-to-speech model trained on the F5-TTS framework, supporting zero-shot voice cloning functionality, released under the Apache 2.0 license for commercial use.

FinSeer StockLLM is an open-source 1-billion-parameter large language model specifically designed for financial time series forecasting, utilizing a Retrieval-Augmented Generation (RAG) framework.

Natural Language ProcessingTransformersEnglish

Skywork Scroll V1 is the first open-source, character-centric advanced video foundation model. Based on the Hunyuan video framework, it is fine-tuned on tens of millions of high-quality film and television clips, and has core advantages such as facial motion capture and cinema-grade lighting aesthetics.

MultimodalDiffusersEnglish

LLaVA-Med is an open-source large vision-language model optimized for biomedical applications, built on the LLaVA framework, enhanced through curriculum learning, and fine-tuned for open-ended biomedical question answering tasks.

MultimodalTransformers

ChemLLM is the first open-source large language model for chemistry and molecular science, built on the InternLM-2 framework, specializing in the field of chemistry and molecular science.

Natural Language ProcessingTransformersMultiple Languages

An open-source large language model with 7 billion parameters based on the Mistral-7B-v1.0 framework, supporting Hebrew and English pre-training

Natural Language ProcessingTransformersMultiple Languages

Gemma is a series of lightweight cutting-edge open-source large language models launched by Google, developed based on the Gemini technology framework, supporting English text generation tasks.

Natural Language ProcessingTransformers

KoGPT2 is a Korean generative pre-trained model based on the Huggingface Transformers framework, developed and open-sourced by SKT-AI.

Natural Language ProcessingTransformers

TransQuest is an open-source translation quality assessment framework that evaluates translation quality without requiring reference translations, supporting both sentence-level and word-level assessments.

Natural Language ProcessingTransformers

TransQuest is an open-source framework for translation quality estimation, supporting both sentence-level and word-level evaluations, and has demonstrated excellent performance in the WMT 2020 Quality Estimation task.

Natural Language ProcessingTransformersOther

TransQuest is an open-source translation quality estimation framework that supports sentence-level and word-level quality estimation, outperforming current state-of-the-art methods.

Natural Language ProcessingTransformers

TransQuest is an open-source framework for translation quality assessment, which won the WMT 2020 sentence-level direct assessment quality assessment shared task.

Natural Language ProcessingTransformers

TransQuest is an open-source translation quality estimation framework that supports evaluating translation quality without reference translations, applicable to multiple language pairs.

Natural Language ProcessingTransformers