DeepSeek Open-Sources DeepSeek-R1 LLM with Performance Comparable To OpenAI's O1 Model

DeepSeek open-sourced DeepSeek-R1, an LLM fine-tuned with reinforcement learning (RL) to enhance reasoning capability. DeepSeek-R1 attains results on par with OpenAI's o1 model on several benchmarks, including MATH-500 and SWE-bench.

DeepSeek-R1 is based on DeepSeek-V3, a mixture of specialists (MoE) design just recently open-sourced by DeepSeek. This base design is fine-tuned utilizing Group Relative Policy Optimization (GRPO), a reasoning-oriented version of RL. The research team also carried out understanding distillation from DeepSeek-R1 to open-source Qwen and Llama designs and launched numerous variations of each; these designs outperform larger designs, including GPT-4, on math and coding criteria.

[DeepSeek-R1 is] the very first step towards improving language design reasoning capabilities using pure reinforcement knowing (RL). Our objective is to check out the capacity of LLMs to develop reasoning abilities without any supervised data, concentrating on their self-evolution through a pure RL process...DeepSeek-R1 ... master a large variety of jobs, consisting of innovative writing, basic question answering, editing, summarization, and more. Additionally, DeepSeek-R1 demonstrates outstanding performance on jobs needing long-context understanding, substantially surpassing DeepSeek-V3 on long-context benchmarks.

To develop the design, surgiteams.com DeepSeek began with DeepSeek-V3 as a base. They initially tried fine-tuning it just with RL, and with no supervised fine-tuning (SFT), producing a model called DeepSeek-R1-Zero, which they have also launched. This model displays strong reasoning efficiency, but" powerful reasoning behaviors, it deals with several concerns. For example, DeepSeek-R1-Zero struggles with challenges like bad readability and language mixing."

To address this, the group used a brief stage of SFT to avoid the "cold start" issue of RL. They collected numerous thousand examples of chain-of-thought reasoning to utilize in SFT of DeepSeek-V3 before running RL. After the RL process converged, they then gathered more SFT information utilizing rejection sampling, wiki.snooze-hotelsoftware.de resulting in a dataset of 800k samples. This dataset was used for further fine-tuning and to produce the distilled models from Llama and Qwen.

DeepSeek examined their design on a range of reasoning, math, higgledy-piggledy.xyz and coding criteria and higgledy-piggledy.xyz compared it to other models, consisting of Claude-3.5- Sonnet, GPT-4o, and o1. DeepSeek-R1 exceeded all of them on numerous of the benchmarks, including AIME 2024 and higgledy-piggledy.xyz MATH-500.

DeepSeek-R1 Performance. Image Source: DeepSeek-R1 Technical Report

Within a few days of its release, the LMArena announced that DeepSeek-R1 was ranked # 3 total in the arena and # 1 in coding and mathematics. It was also connected for # 1 with o1 in "Hard Prompt with Style Control" classification.

Django structure co-creator Simon Willison blogged about his experiments with one of the DeepSeek distilled Llama models on his blog:

Each action starts with a ... pseudo-XML tag containing the chain of thought used to help generate the reaction. [Given the prompt] "a joke about a pelican and a walrus who run a tea space together" ... It then thought for 20 paragraphs before outputting the joke! ... [T] he joke is awful. But the procedure of getting there was such an intriguing insight into how these brand-new designs work.

Andrew Ng's newsletter The Batch discussed DeepSeek-R1:

DeepSeek is quickly emerging as a strong home builder of open designs. Not just are these designs fantastic entertainers, but their license allows use of their outputs for distillation, potentially pressing forward the cutting-edge for language models (and multimodal designs) of all sizes.

The DeepSeek-R1 designs are available on HuggingFace.

About the Author

Anthony Alford

Rate this Article

This material remains in the AI, ML & Data Engineering subject