LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

DeepSeek R1 Distill Qwen 7B GRPO by Dongwei

 »  All LLMs  »  Dongwei  »  DeepSeek R1 Distill Qwen 7B GRPO   URL Share it on

  19   
  Arxiv:2402.03300   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational Dataset:digitallearninggmbh/ma...   Endpoints compatible   Generated from trainer   Grpo   Open-r1   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO 

DeepSeek R1 Distill Qwen 7B GRPO Benchmarks

MMLU Pro: 14.69
GPQA: 3.91
MUSR: 3.55
BBH: 7.88
IFEval: 40.38 vs 88 (so35)-54.1%
LLME Score: 0.3032
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek R1 Distill Qwen 7B GRPO (Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO)

DeepSeek R1 Distill Qwen 7B GRPO Parameters and Internals

LLM NameDeepSeek R1 Distill Qwen 7B GRPO
Repository 🤗https://huggingface.co/Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO 
Model NameDeepSeek-R1-Distill-Qwen-7B-GRPO
Base Model(s)  DeepSeek R1 Distill Qwen 7B   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Model Size7b
Required VRAM15.2 GB
Updated2025-02-07
MaintainerDongwei
Model Typeqwen2
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4   0.0 GB
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.49.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to DeepSeek R1 Distill Qwen 7B GRPO

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB30419183
Qwen2.5 7B RRP 1M986K / 15.2 GB1474
Qwen2.5 7B MixStock V0.1986K / 15.2 GB172
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB522
COCO 7B Instruct 1M986K / 15.2 GB778
SJT 7B V1.1986K / 14.8 GB371
Q2.5 Instruct 1M Harmony986K / 15.2 GB380
Impish QWEN 7B 1M986K / 15.2 GB451
SJT 8B V1.1986K / 17.8 GB160
Qwen2.5 7B DeepSeek R1 1M986K / 15.2 GB698
Note: green Score (e.g. "73.2") means that the model is better than Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO.

Rank the DeepSeek R1 Distill Qwen 7B GRPO Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42801 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer