Qwen1.5 72B Chat GPTQ Int8 by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen1.5 72B Chat GPTQ Int8   URL Share it on

  8-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Gptq   Has space   License:other   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Rank the Qwen1.5 72B Chat GPTQ Int8 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Qwen1.5 72B Chat GPTQ Int8 (Qwen/Qwen1.5-72B-Chat-GPTQ-Int8)

Best Alternatives to Qwen1.5 72B Chat GPTQ Int8

Best Alternatives
HF Rank
Liberated Qwen1.5 72B74.1132K / 144.5 GB446272
SkkuDS DPO 72B V172.8932K / 144.5 GB24210
SkkuDS DPO 72B V372.832K / 144.5 GB24300
Smaug 2 72B69.5132K / 144.5 GB146110
Liberated Qwen1.5 72B 4bit6532K / 45.4 GB150
Liberated Qwen1.5 72B 4bit6532K / 42.6 GB50
Liberated Qwen1.5 72B GGUF6532K / 28.5 GB4290
Liberated Qwen1.5 72B AWQ6532K / 41.3 GB1891
Qwen1.5 72B Chat GPTQ Int432K / 41.3 GB6018631
Qwen1.5 72B Chat GPTQ32K / 45.4 GB52
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-72B-Chat-GPTQ-Int8.

Qwen1.5 72B Chat GPTQ Int8 Parameters and Internals

LLM NameQwen1.5 72B Chat GPTQ Int8
RepositoryOpen on ๐Ÿค— 
Model Size72b
Required VRAM77 GB
Model Typeqwen2
Model Files  3.9 GB: 1-of-20   4.0 GB: 2-of-20   3.9 GB: 3-of-20   4.0 GB: 4-of-20   4.0 GB: 5-of-20   3.9 GB: 6-of-20   4.0 GB: 7-of-20   3.9 GB: 8-of-20   4.0 GB: 9-of-20   4.0 GB: 10-of-20   3.9 GB: 11-of-20   4.0 GB: 12-of-20   3.9 GB: 13-of-20   4.0 GB: 14-of-20   4.0 GB: 15-of-20   3.9 GB: 16-of-20   4.0 GB: 17-of-20   3.9 GB: 18-of-20   3.3 GB: 19-of-20   2.5 GB: 20-of-20
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 35526 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20240042001