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 AWQ by Qwen

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

  229   
  Arxiv:2309.16609   4-bit   Autotrain compatible   Awq   Chat   Conversational   En   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-72B-Chat-AWQ 

Qwen1.5 72B Chat AWQ 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: 0.19803
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 AWQ (Qwen/Qwen1.5-72B-Chat-AWQ)

Qwen1.5 72B Chat AWQ Parameters and Internals

Model Type 
text-generation, chat
Additional Notes 
Stable support of 32K context length for models of all sizes. No need of 'trust_remote_code'.
Supported Languages 
multilingual ()
Training Details 
Methodology:
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.
Input Output 
Input Format:
tokenized input using the tokenizer
Accepted Modalities:
text
Output Format:
text response generation
Performance Tips:
If you encounter code switching or other undesirable results, use provided hyper-parameters in 'generation_config.json'.
LLM NameQwen1.5 72B Chat AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen1.5-72B-Chat-AWQ 
Base Model(s)  Qwen/Qwen1.5-72B-Chat   Qwen/Qwen1.5-72B-Chat
Model Size72b
Required VRAM41.3 GB
Updated2024-12-14
MaintainerQwen
Model Typeqwen2
Model Files  4.0 GB: 1-of-11   4.0 GB: 2-of-11   3.9 GB: 3-of-11   4.0 GB: 4-of-11   4.0 GB: 5-of-11   4.0 GB: 6-of-11   3.9 GB: 7-of-11   4.0 GB: 8-of-11   4.0 GB: 9-of-11   3.0 GB: 10-of-11   2.5 GB: 11-of-11
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen1.5 72B Chat AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Tess V2.5.2 Qwen2 72B AWQ128K / 41.6 GB120
Qwen2.5 72B Instruct AWQ32K / 41.6 GB4891248
Athene V2 Chat AWQ32K / 41.6 GB2554
Qwen2 72B Instruct AWQ32K / 41.6 GB1799537
Qwen2 72B Instruct AWQ GEMM32K / 41.6 GB90
Qwen1.5 72B AWQ32K / 41.3 GB91
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB263
Liberated Qwen1.5 72B AWQ32K / 41.3 GB1001
Ao Karasu 72B AWQ 4bit32K / 41.3 GB142
...in 2.9.2 Qwen2 72B 6.0bpw EXL2128K / 56.1 GB91
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-72B-Chat-AWQ.

Rank the Qwen1.5 72B Chat AWQ 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? 39237 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