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

Qwen1.5 72B Chat by Qwen

 »  All LLMs  »  Qwen  »  Qwen1.5 72B Chat   URL Share it on

  4341   
  Arxiv:2309.16609   Autotrain compatible Base model:finetune:qwen/qwen1...   Base model:qwen/qwen1.5-72b   Chat   Conversational   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-72B-Chat 

Qwen1.5 72B Chat Benchmarks

ARC: 68.52 vs 96.7 (so35)-29.1%
HellaSwag: 86.42 vs 95.3 (gpt4)-9.3%
MMLU: 77.44 vs 88.3 (so35)-12.3%
TruthfulQA: 63.9 vs 59 (gpt4)8.3%
WinoGrande: 79.08 vs 87.5 (gpt4)-9.6%
GSM8K: 20.39 vs 96.4 (so35)-78.8%
LLME Score: 0.22769
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 72B Chat (Qwen/Qwen1.5-72B-Chat)

Qwen1.5 72B Chat Parameters and Internals

Model Type 
text-generation, chat
Additional Notes 
Qwen1.5 is a beta version of Qwen2 with improvements over previously released Qwen including multilingual support and better performance.
Supported Languages 
en (Multilingual support)
Training Details 
Methodology:
Pretrained with a large amount of data, post-trained with supervised finetuning and direct preference optimization.
Context Length:
32000
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention
LLM NameQwen1.5 72B Chat
Repository 🤗https://huggingface.co/Qwen/Qwen1.5-72B-Chat 
Base Model(s)  Qwen/Qwen1.5-72B   Qwen/Qwen1.5-72B
Model Size72b
Required VRAM144.6 GB
Updated2025-02-22
MaintainerQwen
Model Typeqwen2
Model Files  3.8 GB: 1-of-38   3.9 GB: 2-of-38   3.9 GB: 3-of-38   3.6 GB: 4-of-38   3.9 GB: 5-of-38   3.9 GB: 6-of-38   3.9 GB: 7-of-38   3.9 GB: 8-of-38   3.6 GB: 9-of-38   3.9 GB: 10-of-38   3.9 GB: 11-of-38   3.9 GB: 12-of-38   3.9 GB: 13-of-38   3.6 GB: 14-of-38   3.9 GB: 15-of-38   3.9 GB: 16-of-38   3.9 GB: 17-of-38   3.9 GB: 18-of-38   3.6 GB: 19-of-38   3.9 GB: 20-of-38   3.9 GB: 21-of-38   3.9 GB: 22-of-38   3.9 GB: 23-of-38   3.6 GB: 24-of-38   3.9 GB: 25-of-38   3.9 GB: 26-of-38   3.9 GB: 27-of-38   3.9 GB: 28-of-38   3.6 GB: 29-of-38   3.9 GB: 30-of-38   3.9 GB: 31-of-38   3.9 GB: 32-of-38   3.9 GB: 33-of-38   3.6 GB: 34-of-38   3.9 GB: 35-of-38   3.9 GB: 36-of-38   3.9 GB: 37-of-38   2.5 GB: 38-of-38
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen1.5 72B Chat

Model
Likes
Downloads
VRAM
Qwen1.5 72B Chat AWQ2354341 GB
Qwen1.5 72B Chat 4bit22142 GB
Qwen1.5 72B Chat GPTQ2845 GB

Best Alternatives to Qwen1.5 72B Chat

Best Alternatives
Context / RAM
Downloads
Likes
Ultiima 72B128K / 146.1 GB21441
EVA Qwen2.5 72B V0.2128K / 146 GB239416
Qwen2.5 72B128K / 145.5 GB2601058
Ultiima 72B V1.5128K / 146.1 GB1120
AceInstruct 72B128K / 146 GB18714
Homer V1.0 Qwen2.5 72B128K / 146.1 GB1266
Qwen2 72B128K / 145.5 GB9582197
Dolphin 2.9.2 Qwen2 72B128K / 146 GB7661155
...n2.5 72B 2x Instruct TIES V1.0128K / 146.1 GB80
Calme 2.3 Qwen2 72B128K / 146 GB19162
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-72B-Chat.

Rank the Qwen1.5 72B Chat 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? 43470 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