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 GPTQ by LoneStriker

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

  6   
  Arxiv:2309.16609   4bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Gptq   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Qwen1.5-72B-Chat-GPTQ 

Qwen1.5 72B Chat GPTQ 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: 0.15606
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 GPTQ (LoneStriker/Qwen1.5-72B-Chat-GPTQ)
🌟 Advertise your project 🚀

Qwen1.5 72B Chat GPTQ Parameters and Internals

Model Type 
text generation, chat model
Additional Notes 
The beta version does not include GQA and the mixture of SWA and full attention. DPO improves human preference but lowers benchmark evaluation.
Supported Languages 
en (multilingual capabilities include English)
Training Details 
Methodology:
Supervised finetuning and direct preference optimization (DPO)
Context Length:
32000
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention
Input Output 
Accepted Modalities:
text
Performance Tips:
Use provided hyper-parameters in 'generation_config.json' for optimal performance.
LLM NameQwen1.5 72B Chat GPTQ
Repository 🤗https://huggingface.co/LoneStriker/Qwen1.5-72B-Chat-GPTQ 
Base Model(s)  Qwen/Qwen1.5-72B-Chat   Qwen/Qwen1.5-72B-Chat
Model Size72b
Required VRAM45.4 GB
Updated2025-07-30
MaintainerLoneStriker
Model Typeqwen2
Model Files  45.4 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen1.5 72B Chat GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B GPTQ 4bit128K / 45.8 GB10692
Qwen2.5 72B Instruct GPTQ Int432K / 41.6 GB897037
Qwen2 72B Instruct GPTQ Int432K / 41.6 GB3512332
Qwen2.5 72B Instruct GPTQ Int832K / 77 GB125627
Qwen2 72B Instruct GPTQ Int832K / 77 GB12215
Qwen1.5 72B Chat GPTQ Int432K / 41.3 GB187137
Qwen1.5 72B Chat GPTQ Int832K / 77 GB317
Kimi Dev 72B 4bit DWQ128K / 40.9 GB366718
Kimi Dev 72B 8bit128K / 77.1 GB13712
Kimi Dev 72B 5bit128K / 50.1 GB6393
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Qwen1.5-72B-Chat-GPTQ.

Rank the Qwen1.5 72B Chat GPTQ 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? 50262 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