biggy/DeepSeek-R1
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-R1.git synced 2025-04-29 10:29:22 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge 135efdece245997251a566c28ecc206292b9b320 into 45b89c6cb13cf6b01da05ef9a7379f13f8d3baf2

Browse Source
This commit is contained in:
jubinx30 2025-02-18 10:02:33 -05:00 committed by GitHub
commit 3c848aed44
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -1,4 +1,4 @@
# DeepSeek-R1 This is intresting....# DeepSeek-R1
<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html --> <!-- markdownlint-disable html -->
<!-- markdownlint-disable no-duplicate-header --> <!-- markdownlint-disable no-duplicate-header -->
@ -30,7 +30,7 @@
## 1. Introduction ## 1. Introduction
We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. Hello MFs, this is ourgeneration reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.
DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning.
With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.
However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance,
@ -125,7 +125,7 @@ We slightly change their configs and tokenizers. Please use our setting to run t
| | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 | | | Aider-Polyglot (Acc.) | 45.3 | 16.0 | 49.6 | 32.9 | **61.7** | 53.3 |
| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** | | Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
| | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** | | | MATH-500 (Pass@1) | 78.3 | 74.6 | 90.2 | 90.0 | 96.4 | **97.3** |
| | CNMO 2024 (Pass@1) | 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** | | | CNMO 2024 (Pass@1);; 13.1 | 10.8 | 43.2 | 67.6 | - | **78.8** |
| Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** | | Chinese | CLUEWSC (EM) | 85.4 | 87.9 | 90.9 | 89.9 | - | **92.8** |
| | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** | | | C-Eval (EM) | 76.7 | 76.0 | 86.5 | 68.9 | - | **91.8** |
| | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 | | | C-SimpleQA (Correct) | 55.4 | 58.7 | **68.0** | 40.3 | - | 63.7 |
@ -182,6 +182,7 @@ You can also easily start a service using [SGLang](https://github.com/sgl-projec
```bash ```bash
python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B --trust-remote-code --tp 2
``` ```
:w
### Usage Recommendations ### Usage Recommendations