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 Bpw4 EXL2 by blockblockblock

 »  All LLMs  »  blockblockblock  »  Qwen2 72B Instruct Bpw4 EXL2   URL Share it on

  12   
  Arxiv:2309.00071   4-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Exl2   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/blockblockblock/Qwen2-72B-Instruct-bpw4-exl2 

Qwen2 72B Instruct Bpw4 EXL2 Benchmarks

LLME Score: 0.20383
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 Bpw4 EXL2 (blockblockblock/Qwen2-72B-Instruct-bpw4-exl2)

Qwen2 72B Instruct Bpw4 EXL2 Parameters and Internals

Model Type 
text-generation, multimodal
Use Cases 
Areas:
Research, Commercial applications
Supported Languages 
English (high), Chinese (high)
Training Details 
Methodology:
Pretrained with a large amount of data followed by supervised finetuning and direct preference optimization.
Context Length:
131072
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, and an improved tokenizer adaptive to multiple natural languages and codes.
Input Output 
Input Format:
Structured prompts following a chat template
Accepted Modalities:
text
Output Format:
Generated text responses
Performance Tips:
Use rope_scaling for processing longer contexts when necessary
LLM NameQwen2 72B Instruct Bpw4 EXL2
Repository 🤗https://huggingface.co/blockblockblock/Qwen2-72B-Instruct-bpw4-exl2 
Model Size72b
Required VRAM38.7 GB
Updated2024-12-22
Maintainerblockblockblock
Model Typeqwen2
Instruction-BasedYes
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.6 GB: 3-of-5   8.6 GB: 4-of-5   4.3 GB: 5-of-5
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 Bpw4 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
ECE ILAB Q132K / 77.8 GB26010
Qwen2.5 72B Instruct 4bit32K / 40.9 GB178373
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB69853
Athene V2 Chat 4.65bpw H6 EXL232K / 44.3 GB1515
Qwen2.5 72B Instruct 8bit32K / 77.1 GB1134
Qwen2 72B Instruct Bnb 4bit32K / 41.2 GB3657
...struct Mix Calibration 4B EXL232K / 38.8 GB112
Qwen2 72B Instruct Bpw5.5 EXL232K / 51.8 GB111
Qwen2 72B Instruct 4bit32K / 40.9 GB172
...n2 72B Instruct 4.0bpw H6 EXL232K / 38.6 GB161
Note: green Score (e.g. "73.2") means that the model is better than blockblockblock/Qwen2-72B-Instruct-bpw4-exl2.

Rank the Qwen2 72B Instruct Bpw4 EXL2 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? 40066 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