reasoning
DeepSeek-R1
DeepSeek reasoning model; teacher of the R1-Distill models via 800k generated samples. HF tree: 327 finetunes, 122 adapters, 70 quantizations, 5 merges.
Levelmodel
Classreasoning
Parametersnot in the notes
Contextnot in the notes
ReleasedJan 2025
Opennessunknown
Runs onnot in the notes
Statusactive
Lineage
finetunedistillproduct of
DeepSeek-R1-Distill-Llama-70B is a child (distill)high confidencemodel cardDeepSeek-R1-Distill-Llama-8B is a child (distill)high confidencemodel cardDeepSeek-R1-Distill-Qwen-1.5B is a child (distill)high confidencemodel cardDeepSeek-R1-Distill-Qwen-14B is a child (distill)high confidencemodel cardDeepSeek-R1-Distill-Qwen-32B is a child (distill)high confidencemodel cardDeepSeek-R1-Distill-Qwen-7B is a child (distill)high confidencemodel card
Sonar Reasoning Pro is a child (product of)low confidencepress claimWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 14 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- RL stage cost from a secondary report of the Nature supplementary materials; GPU count not stated.
- Context length
- not in the notes
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperDeepSeekstartup, China
DeepSeekstartup, ChinaModelDeepSeek-R1DeepSeek, reasoning
DeepSeek-R1DeepSeek, reasoningR&D TopicsDistillation of Frontier Models into Smaller OnesReasoning via Large-Scale RLSmall-Data Reasoning Fine-Tuning and Distillation
Use CasesIndonesian and Regional-Language LLMsPublic SectorChinese Medical LLMsHealthcareUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs Itnone recordedDeployments of these use cases; none names this model.
Models 7
DeepSeek-R1-Distill-Llama-8BDeepSeek, reasoningdistillDeepSeek-R1-Distill-Qwen-1.5BDeepSeek, reasoningdistillDeepSeek-R1-Distill-Qwen-7BDeepSeek, reasoningdistillDeepSeek-R1-Distill-Llama-70BDeepSeek, reasoningdistillDeepSeek-R1-Distill-Qwen-14BDeepSeek, reasoningdistillDeepSeek-R1-Distill-Qwen-32BDeepSeek, reasoningdistillSonar Reasoning ProPerplexity, reasoningProduct ofOrganisations 1
R&D topics 3
Reasoning via Large-Scale RLReinforcement learning on outcomes, often verifiable math or code, to produce long reason…exemplarDistillation of Frontier Models into Smaller OnesTransferring capability from a large teacher model to a smaller one.exemplarSmall-Data Reasoning Fine-Tuning and DistillationSFT on hundreds to thousands of curated reasoning traces from a stronger model.used by
Sources
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B , Hugging Face huggingface.co https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- meta-llama/Llama-3.1-8B-Instruct , Hugging Face huggingface.co https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
- DeepSeek on the Cover of "Nature": First Response to Controversies Led by LIANG Wenfeng eu.36kr.com https://eu.36kr.com/en/p/3471852231792260
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org https://arxiv.org/abs/2501.12948
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DeepSeek-R1", https://aurion.semai.id/models/deepseek-deepseek-r1/, records of October 2026.