This is the quantized version of kldzj's GPT-OSS-120B-Heretic-v2 model, which is quantized using the imatrix technology of llama.cpp. The model significantly reduces the storage and computing resource requirements through quantization technology while maintaining good model performance, facilitating deployment and operation on various devices.

Natural Language ProcessingGguf

GPT-OSS-120B-Heretic-v2 is a censorship-removed version based on GPT-OSS-120B. It removes the censorship mechanism in the model through targeted ablation operations while maintaining or improving cognitive performance. This version performs excellently in multiple benchmark tests, achieving a balance between intelligence recovery and censorship removal.

Natural Language ProcessingMlx

This is a quantized version of the kldzj/gpt-oss-120b-heretic model, quantized using llamacpp. It offers a variety of quantization types, including special formats such as BF16, Q8_0, and MXFP4_MOE, significantly improving the model's operating efficiency.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the Huihui GPT-OSS-120B-BF16-abliterated-v2 model, specifically optimized for text generation tasks to provide efficient text generation capabilities. The model reduces computational and storage requirements through quantization techniques while maintaining good performance.

Natural Language ProcessingGguf

NVIDIA GPT-OSS-120B Eagle3 is an optimized version based on the OpenAI gpt-oss-120b model. It adopts the Mixture of Experts (MoE) architecture, with a total of 120 billion parameters and 5 billion active parameters. This model supports both commercial and non-commercial use and is suitable for text generation tasks, especially for the development of AI Agent systems, chatbots, and other applications.

Natural Language ProcessingSafetensors

This project distills the inference ability of GPT into the Llama-3.1-8B model through an innovative two-stage training process. First, knowledge distillation and format alignment are performed through supervised fine-tuning, and then reinforcement learning is used to encourage the model to independently explore and optimize inference strategies, focusing on breakthroughs in the field of mathematical reasoning.

Natural Language ProcessingTransformersMultiple Languages

WEBGEN DEVSTRAL IMAGES is an AI model focused on web page generation. It can generate single-page web pages using HTML, CSS, JS, and Tailwind technologies. This project is trained based on custom templates and uses the supervised fine-tuning method, training with a dataset generated by GPT-OSS-120B.

Natural Language ProcessingTransformersEnglish

A three-stage training GRPO inference test model based on the microsoft/phi-4 (14B) base model, fine-tuned through the SFT→RLHF→SFT process, with excellent multi-step reasoning ability

Natural Language ProcessingTransformersMultiple Languages

This is an MLX format version converted from the OpenAI GPT-OSS-120B model, converted using the mlx-lm 0.27.0 tool, and supports efficient text generation tasks.

Natural Language ProcessingMlx

GPT-OSS-120b-GGUF is an open-source text generation model with 120 billion parameters released by OpenAI. It uses the permissive Apache 2.0 license, supports flexible inference intensity configuration and full access to the chain of thought, and has the capabilities of native function call, web browsing, and code execution.

Natural Language ProcessingGguf

A quantized version of the OpenAI GPT-OSS-120B model, quantized using the llama.cpp tool and the imatrix dataset. It offers multiple quantization levels to meet different hardware requirements and supports running in the LM Studio and llama.cpp environments.

Natural Language ProcessingGguf

A large language model optimized based on OpenAI's gpt-oss-120b model. It uses the NEO dataset to improve performance, supports multi-scenario applications, and can run on CPU, GPU, or in partial offloading mode. It has a 128k context length and a mixture of experts architecture with up to 128 experts.

Natural Language ProcessingGgufMultiple Languages

This is a large language model based on the GPT architecture, with 120 billion parameters and compressed using 4-bit quantization technology. It is optimized to run on Apple chips through the MLX framework and supports efficient text generation tasks.

Natural Language ProcessingTransformers

This is the 5-bit quantized version of the OpenAI GPT-OSS-120B model, converted to the MLX format using mlx-lm 0.26.3. This model is a large language model with 120 billion parameters. After quantization, it can run efficiently on Apple Silicon devices.

Natural Language ProcessingMlx

This is a 3-bit quantized version converted from the OpenAI GPT-OSS-120B model, converted to the MLX format using the mlx-lm 0.26.3 tool, suitable for efficient inference on Apple Silicon devices.

Natural Language ProcessingMlx

A 120B parameter text generation model developed by OpenAI, presented through the LM Studio community model program. An 8-bit quantization version is provided, specifically optimized for Apple Silicon chips to support efficient text generation tasks.

Natural Language ProcessingTransformers

This is an experimental quantized version of the OpenAI GPT-OSS-120B model. It uses the Llamacpp framework and the new MXFP4 format for single static quantization processing. It can run under a specific branch and provide efficient support for text generation tasks.

Natural Language ProcessingGguf

The GPT-OSS series is an open-weight model released by OpenAI, designed for powerful reasoning, agent tasks, and diverse developer use cases. The 120B version has 117 billion parameters (5.1 billion of which are active parameters), suitable for production environments and scenarios requiring high reasoning ability.

Natural Language ProcessingTransformers