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 110B by Qwen

 »  All LLMs  »  Qwen  »  Qwen1.5 110B   URL Share it on

  3111   
  Arxiv:2309.16609   Autotrain compatible   Conversational   En   Endpoints compatible   Pretrained   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-110B 

Qwen1.5 110B Benchmarks

MMLU Pro: 48.45
GPQA: 13.65
MUSR: 13.71
BBH: 44.28
IFEval: 34.22 vs 88 (so35)-61.1%
ARC: 69.97 vs 96.7 (so35)-27.6%
HellaSwag: 87.48 vs 95.3 (gpt4)-8.2%
MMLU: 80.2 vs 88.3 (so35)-9.2%
TruthfulQA: 49.66 vs 59 (gpt4)-15.8%
WinoGrande: 84.14 vs 87.5 (gpt4)-3.8%
GSM8K: 81.05 vs 96.4 (so35)-15.9%
MATH Lvl 5: 24.77
LLME Score: 0.34006
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 110B (Qwen/Qwen1.5-110B)

Qwen1.5 110B Parameters and Internals

Model Type 
decoder-only, language model, transformer-based, pretrained
Supported Languages 
en (Multilingual support)
Training Details 
Methodology:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention.
Context Length:
32000
Model Architecture:
Transformer with SwiGLU activation and improved tokenizer adaptive to multiple natural languages and codes.
LLM NameQwen1.5 110B
Repository 🤗https://huggingface.co/Qwen/Qwen1.5-110B 
Model Size110b
Required VRAM221.7 GB
Updated2024-12-26
MaintainerQwen
Model Typeqwen2
Model Files  7.9 GB: 1-of-30   7.3 GB: 2-of-30   7.3 GB: 3-of-30   7.3 GB: 4-of-30   8.0 GB: 5-of-30   7.2 GB: 6-of-30   7.3 GB: 7-of-30   7.3 GB: 8-of-30   8.0 GB: 9-of-30   7.2 GB: 10-of-30   7.3 GB: 11-of-30   7.3 GB: 12-of-30   8.0 GB: 13-of-30   7.2 GB: 14-of-30   7.3 GB: 15-of-30   7.3 GB: 16-of-30   8.0 GB: 17-of-30   7.2 GB: 18-of-30   7.3 GB: 19-of-30   7.3 GB: 20-of-30   8.0 GB: 21-of-30   7.2 GB: 22-of-30   7.3 GB: 23-of-30   7.3 GB: 24-of-30   8.0 GB: 25-of-30   7.2 GB: 26-of-30   7.3 GB: 27-of-30   7.3 GB: 28-of-30   8.0 GB: 29-of-30   5.1 GB: 30-of-30
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 110B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 110B Chat32K / 158.3 GB6356123
Airoboros 110B 3.332K / 158.3 GB3582
Dolphin 2.9.1 Qwen 110B32K / 193.4 GB4626
Airoboros DPO 110B 3.332K / 158.3 GB270
Aqua Qwen 0.1 110B32K / 198.3 GB170
...wen 1.5 110B Layer Mix Bpw 2.28K / 40.7 GB171
Qwen1.5 110B Chat 4bit32K / 62.2 GB115
Qwen1.5 110B Chat 8bit32K / 179.8 GB141
...n1.5 110B Chat 3.35bpw H6 EXL232K / 49 GB121
...n1.5 110B Chat 3.25bpw H6 EXL232K / 47.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-110B.

Rank the Qwen1.5 110B 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? 40303 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