Ko R1 14B V2.0.3 by OLAIR

 »  All LLMs  »  OLAIR  »  Ko R1 14B V2.0.3   URL Share it on

  Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Conversational Dataset:olair/open-r1-ko-sft-v...   Endpoints compatible   Ko   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Ko R1 14B V2.0.3 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Ko R1 14B V2.0.3 Parameters and Internals

LLM NameKo R1 14B V2.0.3
Repository 🤗https://huggingface.co/OLAIR/ko-r1-14b-v2.0.3 
Base Model(s)  DeepSeek R1 Distill Qwen 14B   deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Model Size14b
Required VRAM59 GB
Updated2025-08-26
MaintainerOLAIR
Model Typeqwen2
Model Files  4.7 GB: 1-of-12   5.0 GB: 2-of-12   4.9 GB: 3-of-12   5.0 GB: 4-of-12   4.9 GB: 5-of-12   5.0 GB: 6-of-12   4.9 GB: 7-of-12   5.0 GB: 8-of-12   4.9 GB: 9-of-12   5.0 GB: 10-of-12   4.9 GB: 11-of-12   4.8 GB: 12-of-12
Supported Languagesko
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.49.0
Tokenizer ClassLlamaTokenizerFast
Padding Token<|end▁of▁sentence|>
Vocabulary Size151665
Torch Data Typefloat32

Best Alternatives to Ko R1 14B V2.0.3

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB15400318
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB85228
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB108
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
Qwen2.5 14B YOYO V4986K / 29.7 GB145
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB118
Etr1o V1.2986K / 29.7 GB80
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB154
Impish QWEN 14B 1M986K / 29.7 GB1917
Note: green Score (e.g. "73.2") means that the model is better than OLAIR/ko-r1-14b-v2.0.3.

Rank the Ko R1 14B V2.0.3 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? 50900 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124