QwQ-32B-Snowdrop-v0.5-Type-S
One of three experimental merges in an attempt to make Snowdrop v1. Samplers: temperature at 0.9, minp at...
One of three experimental merges in an attempt to make Snowdrop v1. Samplers: temperature at 0.9, minp at...
ZeroXClem-Qwen2.5-7B-HomerFuse-NerdExp is a powerful and finely-tuned AI model built on HomerSlerp6-7B, with a fusion of Qwen2.5-7B-based models to...
This model is described in the paper LocAgent: Graph-Guided LLM Agents for Code Localization. LocAgent uses a graph-based...
> Delta-Pavonis-Qwen-14B is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of...
This is a merge of pre-trained language models created using mergekit. This model was merged using the Model...
This is a merge of pre-trained language models created using mergekit. This model was merged using the Model...
The Model mlx-community/qwq-bakeneko-32b-8bit was converted to MLX format from rinna/qwq-bakeneko-32b using mlx-lm version 0.21.5. Модальности:Генерация текста Области применения:Диалог...
OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe...
The Model mlx-community/OlympicCoder-7B-4bit was converted to MLX format from open-r1/OlympicCoder-7B using mlx-lm version 0.21.5. Модальности:Генерация текста Области применения:Диалог...
This model has been uncensored to remove political bias, not unsafe content. For example, the current qwq 32b...