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

Qwen2 72B Instruct EXL2 8.0bpw by bullerwins

 »  All LLMs  »  bullerwins  »  Qwen2 72B Instruct EXL2 8.0bpw   URL Share it on

  9   
  Arxiv:2309.00071   8-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Exl2   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bullerwins/Qwen2-72B-Instruct_exl2_8.0bpw 

Qwen2 72B Instruct EXL2 8.0bpw Benchmarks

LLME Score: 0.19082
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 72B Instruct EXL2 8.0bpw (bullerwins/Qwen2-72B-Instruct_exl2_8.0bpw)

Qwen2 72B Instruct EXL2 8.0bpw Parameters and Internals

Model Type 
text generation, instruction-tuned
Additional Notes 
Supports context length up to 131,072 tokens. Enhanced model length extrapolation with YARN for processing extensive inputs.
Supported Languages 
en (English proficiency)
Training Details 
Methodology:
Pretrained with a large amount of data, post-trained with supervised finetuning and direct preference optimization.
Context Length:
131072
Model Architecture:
Transformer with SwiGLU activation, attention QKV bias, group query attention.
LLM NameQwen2 72B Instruct EXL2 8.0bpw
Repository 🤗https://huggingface.co/bullerwins/Qwen2-72B-Instruct_exl2_8.0bpw 
Model Size72b
Required VRAM66.9 GB
Updated2025-02-22
Maintainerbullerwins
Model Typeqwen2
Instruction-BasedYes
Model Files  8.4 GB: 1-of-8   8.4 GB: 2-of-8   8.4 GB: 3-of-8   8.4 GB: 4-of-8   8.6 GB: 5-of-8   8.4 GB: 6-of-8   8.6 GB: 7-of-8   7.7 GB: 8-of-8
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 72B Instruct EXL2 8.0bpw

Best Alternatives
Context / RAM
Downloads
Likes
ECE ILAB Q132K / 77.8 GB18890
Qwen2.5 72B Instruct 4bit32K / 40.9 GB1442605
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB106387
Athene V2 Chat 4.65bpw H6 EXL232K / 44.3 GB196
Qwen2.5 72B Instruct 8bit32K / 77.1 GB655
Qwen2 72B Instruct Bnb 4bit32K / 41.2 GB2127
Qwen2 72B Instruct EXL2 8.0bpw32K / 65.6 GB381
...struct Mix Calibration 4B EXL232K / 38.8 GB102
Qwen2 72B Instruct Bpw5.5 EXL232K / 51.8 GB71
Qwen2 72B Instruct Bpw4 EXL232K / 38.7 GB80
Note: green Score (e.g. "73.2") means that the model is better than bullerwins/Qwen2-72B-Instruct_exl2_8.0bpw.

Rank the Qwen2 72B Instruct EXL2 8.0bpw 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