CodeV is a 7-billion-parameter vision-language model fine-tuned based on Qwen2.5-VL-7B-Instruct. Through two-stage training of supervised fine-tuning (SFT) and reinforcement learning (RL) based on tool-aware policy optimization (TAPO), it aims to achieve reliable and interpretable visual reasoning. It represents visual tools as executable Python code and ensures the consistency between tool usage and question evidence through a reward mechanism, solving the problem of irrelevant tool invocation under high accuracy.

MultimodalTransformersMultiple Languages

ActIO-UI-7B-RLVR is a 7-billion-parameter visual language model released by Uniphore, specifically designed for computer interface automation tasks. It is based on Qwen2.5-VL-7B-Instruct and optimized through supervised fine-tuning and reinforcement learning with verifiable rewards. It performs excellently in tasks such as GUI navigation, element positioning, and interaction planning, and has achieved the leading level among open-source 7B models in the WARC-Bench benchmark test.

MultimodalTransformersEnglish

Z-Image-Re-Turbo is a text-to-image generation model that has been optimized for de-reduction and re-acceleration based on the Z-Image-De-Turbo model. This model aims to balance the convenience during training and the speed during inference. It restores the fast generation ability close to the original Turbo model while maintaining the same training-friendly features as Z-Image-De-Turbo, enabling it to be perfectly compatible with a large number of trained LoRA models in the Z-Image ecosystem.

MultimodalDiffusers

This is the GGUF quantization format version of the NousResearch/Hermes-4.3-36B model, quantized by MaziyarPanahi. GGUF is an efficient model format designed to optimize local deployment and inference performance, supporting multiple quantization levels (2-bit to 8-bit), and suitable for a wide range of text generation tasks.

Natural Language ProcessingGguf

OpenThinker-Agent-v1-SFT is an agent model obtained through supervised fine-tuning (SFT) based on Qwen/Qwen3-8B. It is the first-stage model of the complete training process (SFT + RL) of OpenThinker-Agent-v1, specifically optimized for agent tasks (such as terminal operations and code repair).

Natural Language ProcessingTransformersOther

OpenThinker - Agent - v1 is an open - source intelligent agent model that is subsequently trained based on Qwen3 - 8B. It is designed for terminal operations and software engineering tasks. It is first trained on a high - quality supervised fine - tuning dataset and then further optimized through reinforcement learning. It performs excellently in agent benchmark tests such as Terminal - Bench 2.0 and SWE - Bench.

Natural Language ProcessingTransformersOther

This is a CrossEncoder model developed by Redis and fine-tuned for the LangCache semantic caching task. It is based on the mature `cross-encoder/ms-marco-MiniLM-L6-v2` model and trained on a dataset of over 1 million LangCache sentence pairs. It is specifically designed to calculate the semantic relevance score between two texts to optimize the cache hit rate.

Natural Language ProcessingSentence-transformersEnglish

GigaChat3-10B-A1.8B is an efficient dialogue model in the GigaChat series. Based on the Mixture-of-Experts (MoE) architecture, it has a total of 10 billion parameters and 1.8 billion active parameters. It adopts the innovative Multi-head Latent Attention (MLA) and Multi-token Prediction (MTP) technologies, aiming to optimize inference throughput and generation speed. The model is trained on 20T tokens of diverse data and supports 10 languages including Chinese, suitable for dialogue scenarios requiring quick responses.

Natural Language ProcessingGgufMultiple Languages

Hito 1.7B is a GGUF quantized version model optimized for tools such as llama.cpp, Ollama, and LM Studio. It has 1.7 billion parameters and uses the Nested Cognitive Reasoning (NCR) method, enabling a structured and self-correcting thinking mode to improve the accuracy and transparency of reasoning.

Natural Language ProcessingGgufEnglish

Rnj-1-instruct is an 8-billion-parameter open-weight dense model trained from scratch by Essential AI. It is optimized for code, STEM fields, agent capabilities, and tool invocation. It performs excellently in multiple programming languages and also demonstrates strong capabilities in mathematics and science, comparable to the most advanced open-weight models.

Natural Language ProcessingTransformers

This model is an MLX format conversion version of the Ministral-3-3B-Instruct-2512 instruction fine-tuning model released by Mistral AI. It is a large language model with a parameter scale of 3B, specifically optimized for following instructions and dialogue tasks, and supports multiple languages. The MLX format enables it to run efficiently on Apple Silicon devices.

Natural Language ProcessingMlxMultiple Languages

This is a lightweight text generation model based on the Meta LLaMA 3 8B model. It is efficiently fine-tuned using the Unsloth framework and converted to the GGUF format. The model is optimized for the Alpaca dataset, suitable for local deployment and inference, especially in resource-constrained environments.

Natural Language ProcessingGguf

This project provides a text generation model fine-tuned based on the Microsoft Phi-3.5-mini-instruct model, which has been converted to the GGUF format and is suitable for the llama.cpp inference framework. The model was fine-tuned on the philschmid/guanaco-sharegpt-style dataset, optimizing its instruction-following and dialogue capabilities, and is suitable for efficient text generation tasks in resource-constrained environments.

Natural Language ProcessingGguf

Z-Image-Turbo is an image processing model quantized in FP8 E5M2 and E4M3FN formats. It is optimized based on the original Tongyi-MAI/Z-Image-Turbo model, significantly reducing the model size and inference resource requirements while maintaining performance.

MultimodalDiffusersEnglish

This is a video understanding model fine-tuned based on the VideoMAE-base architecture, specifically optimized for sign language recognition tasks. The model was trained on the WLASL dataset for 200 epochs, using the TimeSformer architecture to process video sequences.

Computer VisionTransformers

This is a video understanding model fine-tuned based on the VideoMAE-base architecture, specifically optimized for sign language recognition tasks. The model was trained on the WLASL100 dataset for 200 epochs and has the ability to recognize video actions.

Computer VisionTransformers

FLUX.2-dev is an image generation and editing model developed by black-forest-labs. It has been converted to the GGUF format, optimized specifically for image generation tasks, and adopts a diffusion model architecture. It supports use in the ComfyUI framework.

MultimodalGguf

An optimized image generation model based on black-forest-labs/FLUX.2-dev, supporting image-to-image generation and editing tasks. It uses fp8_scaled quantization technology to improve inference speed and is particularly suitable for use on low-VRAM GPUs.

This is a quantized version of the Microsoft Fara-7B model, optimized using the imatrix technology of llama.cpp. The model supports multiple quantization levels, from high-precision bf16 to extremely low-precision IQ2_M, meeting the needs of different hardware configurations and performance requirements.

Natural Language ProcessingGguf

This model is an MLX format conversion version of Kimi-Linear-48B-A3B-Instruct, optimized for Apple Silicon devices such as the Apple Mac Studio. It is a large language model with 48 billion parameters, supporting instruction following and suitable for local inference and conversation tasks.

Natural Language ProcessingMlx