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

Qwen2.5 14B Instruct 1M GRPO Reasoning by notbdq

 »  All LLMs  »  notbdq  »  Qwen2.5 14B Instruct 1M GRPO Reasoning   URL Share it on

  25   
  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/notbdq/Qwen2.5-14B-Instruct-1M-GRPO-Reasoning 

Qwen2.5 14B Instruct 1M GRPO Reasoning Benchmarks

MMLU Pro: 42.77
GPQA: 12.42
MUSR: 11.35
BBH: 45.66
IFEval: 84.14 vs 88 (so35)-4.4%
MATH Lvl 5: 53.02
LLME Score: 0.34636
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Qwen2.5 14B Instruct 1M GRPO Reasoning Parameters and Internals

LLM NameQwen2.5 14B Instruct 1M GRPO Reasoning
Repository 🤗https://huggingface.co/notbdq/Qwen2.5-14B-Instruct-1M-GRPO-Reasoning 
Model Size14b
Required VRAM29.7 GB
Updated2025-06-11
Maintainernotbdq
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.7 GB: 6-of-6
Model ArchitectureQwen2ForCausalLM
Context Length1010000
Model Max Length1010000
Transformers Version4.48.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace
Qwen2.5 14B Instruct 1M GRPO Reasoning (notbdq/Qwen2.5-14B-Instruct-1M-GRPO-Reasoning)

Best Alternatives to Qwen2.5 14B Instruct 1M GRPO Reasoning

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB112812308
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB88928
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB9156
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB518
Qwen2.5 14B YOYO V4986K / 29.7 GB204
Impish QWEN 14B 1M986K / 29.7 GB5017
Q2.5 14B Instruct 1M Harmony986K / 29.7 GB151
Calcium Opus 14B Elite 1M986K / 29.7 GB194
Note: green Score (e.g. "73.2") means that the model is better than notbdq/Qwen2.5-14B-Instruct-1M-GRPO-Reasoning.

Rank the Qwen2.5 14B Instruct 1M GRPO Reasoning 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? 48079 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 v20241124
  Support LLM Explorer