LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Qwen1.5 14B Chat by Qwen

What open-source LLMs or SLMs are you in search of? 18870 in total.

 ยป  All LLMs  ยป  Qwen  ยป  Qwen1.5 14B Chat   URL Share it on

  Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Has space   License:other   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Rank the Qwen1.5 14B Chat 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 14B Chat (Qwen/Qwen1.5-14B-Chat)

Quantized Models of the Qwen1.5 14B Chat

Model
Likes
Downloads
VRAM
Qwen1.5 14B Chat AWQ742679 GB
Qwen1.5 14B Chat AWQ099 GB

Best Alternatives to Qwen1.5 14B Chat

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Blossom V4 Qwen1 5 14B66.7432K / 28.4 GB770
Qwen1.5 14B66.732K / 28.3 GB308010
Quyen Pro V0.132K / 28.4 GB455
Qwen1.5 14B Chat 5bpw EXL232K / 10.1 GB31
Qwen1.5 14B Chat 8bpw H8 EXL232K / 15 GB11
Qwen1.5 14B Chat GPTQ Int432K / 9.7 GB110711
Qwen1.5 14B Chat AWQ32K / 9.7 GB42677
Qwen1.5 14B Chat AWQ32K / 9.7 GB90
Qwen1.5 14B Chat GPTQ Int832K / 16.1 GB2942
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-14B-Chat.

Qwen1.5 14B Chat Parameters and Internals

LLM NameQwen1.5 14B Chat
RepositoryOpen on ๐Ÿค— 
Model Size14b
Required VRAM28.3 GB
Updated2024-02-29
MaintainerQwen
Model Typeqwen2
Model Files  3.9 GB: 1-of-8   4.0 GB: 2-of-8   3.9 GB: 3-of-8   3.9 GB: 4-of-8   3.9 GB: 5-of-8   4.0 GB: 6-of-8   3.1 GB: 7-of-8   1.6 GB: 8-of-8
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Initializer Range0.02
Torch Data Typebfloat16
Errorsreplace
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003