DeepSeek
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
-
Chat with DeepSeek-VL2-small
🌍608Chat with an AI using text and images for visual answers
-
deepseek-ai/deepseek-vl2-tiny
Image-Text-to-Text • 3B • Updated • 1.19M • 248 -
deepseek-ai/deepseek-vl2-small
Image-Text-to-Text • 16B • Updated • 7.62k • 180 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • 27B • Updated • 3.65k • 388
DeepSeek-Prover-Series
-
deepseek-ai/DeepSeek-Coder-V2-Instruct
Text Generation • 236B • Updated • 7.25k • 698 -
deepseek-ai/DeepSeek-Coder-V2-Base
Text Generation • 236B • Updated • 2.18k • 82 -
deepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • 16B • Updated • 5.91k • 114 -
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Text Generation • 16B • Updated • 542k • 628
DeepSeek-VL model series
DeepSeek LLM series
DeepSeek MoE series
-
deepseek-ai/DeepSeek-V3.2-Exp
Text Generation • 685B • Updated • 214k • • 994 -
deepseek-ai/DeepSeek-V3.2-Exp-Base
Text Generation • 685B • Updated • 426 • 68 -
deepseek-ai/DeepSeek-V3.2
Text Generation • 685B • Updated • 1.19M • • 1.46k -
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation • 685B • Updated • 5.14k • • 720
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 9.41M • • 13.5k -
deepseek-ai/DeepSeek-R1-Zero
Text Generation • 685B • Updated • 6.3k • 959 -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 411k • • 794 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 727k • • 1.59k
DeepSeek Math series
-
deepseek-ai/DeepSeek-Math-V2
Text Generation • 685B • Updated • 419 • 706 -
deepseek-ai/deepseek-math-7b-instruct
Text Generation • Updated • 12.1k • 153 -
deepseek-ai/deepseek-math-7b-rl
Text Generation • 7B • Updated • 1.28k • 96 -
deepseek-ai/deepseek-math-7b-base
Text Generation • Updated • 2.01k • 89
Janus is a novel autoregressive framework that unifies multimodal understanding and generation.
-
deepseek-ai/DeepSeek-V2-Chat-0628
Text Generation • 236B • Updated • 4.87k • 179 -
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 10.4k • 462 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 10.2k • 334 -
deepseek-ai/DeepSeek-V2-Lite
Text Generation • 16B • Updated • 485k • 183
models for paper expert-specialized fine-tuning
DeepSeek Coder series
-
deepseek-ai/deepseek-coder-33b-instruct
Text Generation • 33B • Updated • 2.74k • 580 -
deepseek-ai/deepseek-coder-6.7b-instruct
Text Generation • 7B • Updated • 535k • 507 -
deepseek-ai/deepseek-coder-7b-instruct-v1.5
Text Generation • 7B • Updated • 595k • 158 -
deepseek-ai/deepseek-coder-1.3b-instruct
Text Generation • 1B • Updated • 111k • 176
-
deepseek-ai/DeepSeek-V3.2-Exp
Text Generation • 685B • Updated • 214k • • 994 -
deepseek-ai/DeepSeek-V3.2-Exp-Base
Text Generation • 685B • Updated • 426 • 68 -
deepseek-ai/DeepSeek-V3.2
Text Generation • 685B • Updated • 1.19M • • 1.46k -
deepseek-ai/DeepSeek-V3.2-Speciale
Text Generation • 685B • Updated • 5.14k • • 720
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 9.41M • • 13.5k -
deepseek-ai/DeepSeek-R1-Zero
Text Generation • 685B • Updated • 6.3k • 959 -
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
Text Generation • 71B • Updated • 411k • • 794 -
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation • 33B • Updated • 727k • • 1.59k
DeepSeek Math series
-
deepseek-ai/DeepSeek-Math-V2
Text Generation • 685B • Updated • 419 • 706 -
deepseek-ai/deepseek-math-7b-instruct
Text Generation • Updated • 12.1k • 153 -
deepseek-ai/deepseek-math-7b-rl
Text Generation • 7B • Updated • 1.28k • 96 -
deepseek-ai/deepseek-math-7b-base
Text Generation • Updated • 2.01k • 89
-
Chat with DeepSeek-VL2-small
🌍608Chat with an AI using text and images for visual answers
-
deepseek-ai/deepseek-vl2-tiny
Image-Text-to-Text • 3B • Updated • 1.19M • 248 -
deepseek-ai/deepseek-vl2-small
Image-Text-to-Text • 16B • Updated • 7.62k • 180 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • 27B • Updated • 3.65k • 388
Janus is a novel autoregressive framework that unifies multimodal understanding and generation.
DeepSeek-Prover-Series
-
deepseek-ai/DeepSeek-V2-Chat-0628
Text Generation • 236B • Updated • 4.87k • 179 -
deepseek-ai/DeepSeek-V2-Chat
Text Generation • 236B • Updated • 10.4k • 462 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 10.2k • 334 -
deepseek-ai/DeepSeek-V2-Lite
Text Generation • 16B • Updated • 485k • 183
-
deepseek-ai/DeepSeek-Coder-V2-Instruct
Text Generation • 236B • Updated • 7.25k • 698 -
deepseek-ai/DeepSeek-Coder-V2-Base
Text Generation • 236B • Updated • 2.18k • 82 -
deepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • 16B • Updated • 5.91k • 114 -
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
Text Generation • 16B • Updated • 542k • 628
models for paper expert-specialized fine-tuning
DeepSeek-VL model series
DeepSeek Coder series
-
deepseek-ai/deepseek-coder-33b-instruct
Text Generation • 33B • Updated • 2.74k • 580 -
deepseek-ai/deepseek-coder-6.7b-instruct
Text Generation • 7B • Updated • 535k • 507 -
deepseek-ai/deepseek-coder-7b-instruct-v1.5
Text Generation • 7B • Updated • 595k • 158 -
deepseek-ai/deepseek-coder-1.3b-instruct
Text Generation • 1B • Updated • 111k • 176
DeepSeek LLM series
DeepSeek MoE series