CoolFace
20 results

r1-zero

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “r1-zero”
deepseek-ai /DeepSeek-R1-Zerotext-generationtransformers966 likes12k downloads2y agoHugging Facemradermacher /DeepICD-R1-zero-32B-i1-GGUFreinforcement-learningtransformersen0 likes1.5k downloads6mo agoHugging Facemradermacher /VisualThinker-R1-Zero-i1-GGUFtransformersen0 likes1k downloads1y agoHugging Facemradermacher /Omni-R1-Zero-i1-GGUFtransformersrl0 likes1k downloads8mo agoHugging Facemradermacher /Omni-R1-Zero-GGUFtransformersrl0 likes482 downloads8mo agoHugging Faceunsloth /DeepSeek-R1-Zero-GGUFtransformersen27 likes438 downloads2y agoHugging Facemradermacher /DeepICD-R1-zero-32B-GGUFreinforcement-learningtransformersen0 likes362 downloads6mo agoHugging Facemradermacher /Table-R1-Zero-8B-GGUFtransformersen2 likes358 downloads1y agoHugging Face

Datasets

All datasets matching “r1-zero”
ZeroAgency /ru-thinking-reasoning-r1-v2-dedupedtext100K<n<1M1 likes211 downloads2y agoHugging FaceZeroAgency /ru-thinking-reasoning-r1Combined dataset of mostly Russian thinking/reasoning/reflection dialogs in form of conversation suitable for LLM fine-tuning scenarios. All responses are mapped to same format. The format of reasoning in most cases is: <think> Reasoning... </think> Response For reflection dataset - there can be also <reflection> tags inside <think>. Common system prompt for think: Ты полезный ассистент. Отвечай на вопросы, сохраняя следующую структуру: <think> Твои мысли и рассуждения </think> Твой конечный… See the full description on the dataset page: https://huggingface.co/datasets/ZeroAgency/ru-thinking-reasoning-r1.texttext-generation100K<n<1M1 likes125 downloads2y agoHugging FaceZeroAgency /ru-thinking-reasoning-r1-v2This is a modified version of ZeroAgency/ru-thinking-reasoning-r1 with addition of Egor-AI/CoT-XLang dataset. Combined dataset of mostly Russian thinking/reasoning/reflection dialogs in form of conversation suitable for LLM fine-tuning scenarios. All responses are mapped to same format. The format of reasoning in most cases is: <think> Reasoning... </think> Response For reflection dataset - there can be also <reflection> tags inside <think>. Common system prompt for think: Ты полезный… See the full description on the dataset page: https://huggingface.co/datasets/ZeroAgency/ru-thinking-reasoning-r1-v2.texttext-generation100K<n<1M0 likes109 downloads2y agoHugging FaceTable-R1 /Table-R1-Zero-Datasettext10K<n<100K0 likes65 downloads1y agoHugging FaceAllen-UQ /trn-r1-zero-tags0 likes63 downloads5mo agoHugging FaceZeroAgency /ru-thinking-reasoning-r1-dedupedtext100K<n<1M1 likes34 downloads2y agoHugging Face

Apps

All apps matching “r1-zero”
supercyx3 /deepseek-ai-DeepSeek-R1-Zerogradio2 likes2y agoHugging Faceduzaq /deepseek-ai-DeepSeek-R1-Zerogradio0 likes2y agoHugging FaceSoulSeeker /deepseek-ai-DeepSeek-R1-Zerogradio1 likes2y agoHugging Facemb00md /DeepSeek-R1-Zerodocker0 likes2y agoHugging FaceBodArtist /deepseek-ai-DeepSeek-R1-Zerogradio0 likes2y agoHugging FaceAnachroni-co /deepseek-ai-DeepSeek-R1-Zerostreamlit0 likes2y agoHugging Face