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 72B Instruct GPTQ Int4 by Qwen

 »  All LLMs  »  Qwen  »  Qwen2.5 72B Instruct GPTQ Int4   URL Share it on

  49958   
  Arxiv:2309.00071   Arxiv:2407.10671   4-bit   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-72b-in...   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4 

Qwen2.5 72B Instruct GPTQ Int4 Benchmarks

LLME Score: 0.33596
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 72B Instruct GPTQ Int4 (Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4)

Qwen2.5 72B Instruct GPTQ Int4 Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
This model is quantized to 4-bit with GPTQ for efficient operation.
Supported Languages 
languages_supported (Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more), proficiency ()
Training Details 
Methodology:
Pretraining & Post-training with transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Context Length:
131072
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Input Output 
Input Format:
JSON or text prompts with a role-play implementation
Accepted Modalities:
text
Output Format:
Text responses
Performance Tips:
Add rope_scaling configuration for handling long contexts.
LLM NameQwen2.5 72B Instruct GPTQ Int4
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4 
Base Model(s)  Qwen/Qwen2.5-72B-Instruct   Qwen/Qwen2.5-72B-Instruct
Model Size72b
Required VRAM41.6 GB
Updated2024-12-21
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  3.9 GB: 1-of-11   3.9 GB: 2-of-11   4.0 GB: 3-of-11   4.0 GB: 4-of-11   3.9 GB: 5-of-11   4.0 GB: 6-of-11   4.0 GB: 7-of-11   3.9 GB: 8-of-11   4.0 GB: 9-of-11   3.5 GB: 10-of-11   2.5 GB: 11-of-11
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2.5 72B Instruct GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 72B Instruct GPTQ Int832K / 77 GB1025513
Qwen2 72B Instruct GPTQ Int832K / 77 GB1070814
Qwen2 72B Instruct GPTQ Int432K / 41.6 GB518631
ECE ILAB Q132K / 77.8 GB26390
Qwen2.5 72B Instruct 4bit32K / 40.9 GB175763
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB65913
Athene V2 Chat 4.65bpw H6 EXL232K / 44.3 GB1495
Qwen2.5 72B Instruct 8bit32K / 77.1 GB1164
Qwen2 72B Instruct Bnb 4bit32K / 41.2 GB3597
...struct Mix Calibration 4B EXL232K / 38.8 GB112
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4.

Rank the Qwen2.5 72B Instruct GPTQ Int4 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? 40013 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 v20241217
  Support LLM Explorer