Qwen2.5 14B by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2.5 14B   URL Share it on

  Arxiv:2407.10671   Conversational   En   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Qwen/Qwen2.5-14B 

Qwen2.5 14B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 14B (Qwen/Qwen2.5-14B)

Qwen2.5 14B Parameters and Internals

Model Type 
causal language model
Additional Notes 
We do not recommend using base language models for conversations.
Supported Languages 
English (proficient), Chinese (proficient), French (proficient), Spanish (proficient), Portuguese (proficient), German (proficient), Italian (proficient), Russian (proficient), Japanese (proficient), Korean (proficient), Vietnamese (proficient), Thai (proficient), Arabic (proficient)
Training Details 
Methodology:
Pretraining
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
LLM NameQwen2.5 14B
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen2.5-14B 
Model Size14b
Required VRAM29.6 GB
Updated2025-03-12
MaintainerQwen
Model Typeqwen2
Model Files  3.9 GB: 1-of-8   4.0 GB: 2-of-8   4.0 GB: 3-of-8   4.0 GB: 4-of-8   4.0 GB: 5-of-8   4.0 GB: 6-of-8   4.0 GB: 7-of-8   1.7 GB: 8-of-8
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 14B

Model
Likes
Downloads
VRAM
Qwen2.5 14B Unsloth Bnb 4bit1679012 GB
Qwen2.5 14B Instruct 4bit92744038 GB
Qwen2.5 14B Bnb 4bit517469 GB
Qwen2.5 14B Instruct 8bit26515 GB

Best Alternatives to Qwen2.5 14B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB54681278
Condor Opus 14B Exp986K / 29.7 GB29211
Qwen2.5 14B YOYO V4986K / 29.7 GB3523
Lacerta Opus 14B Elite8986K / 29.7 GB34111
Tadpole Opus 14B Exp986K / 29.7 GB45310
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB3265
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2203
Etr1o V1.2986K / 29.7 GB1380
Calcium Opus 14B Elite 1M986K / 29.7 GB82913
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB3224
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-14B.

Rank the Qwen2.5 14B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 44949 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227