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 MoE A2.7B Wikihow by MaziyarPanahi

 »  All LLMs  »  MaziyarPanahi  »  Qwen1.5 MoE A2.7B Wikihow   URL Share it on

  16   
  Autotrain compatible Base model:finetune:qwen/qwen1... Base model:qwen/qwen1.5-moe-a2...   Conversational   Cosmopedia Dataset:huggingfacetb/cosmoped...   Endpoints compatible   Finetuned   Generated from trainer   Moe   Qwen   Qwen2 moe   Region:us   Safetensors   Sharded   Tensorflow   Wikihow
Model Card on HF 🤗: https://huggingface.co/MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow 

Qwen1.5 MoE A2.7B Wikihow Benchmarks

MMLU Pro: 15.34
GPQA: 3.36
MUSR: 2.01
BBH: 15.47
IFEval: 29.54 vs 88 (so35)-66.4%
MATH Lvl 5: 8.23
LLME Score: 0.17734
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 MoE A2.7B Wikihow (MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow)
🌟 Advertise your project 🚀

Qwen1.5 MoE A2.7B Wikihow Parameters and Internals

Model Type 
text-generation
Additional Notes 
Refer to the latest leaderboard evaluation and training config for more in-depth insights.
Training Details 
Data Sources:
HuggingFaceTB/cosmopedia
Data Volume:
Not Specified
Methodology:
Fine-tuned
Context Length:
2048
Training Time:
Not Specified
Hardware Used:
multi-GPU
Model Architecture:
Qwen1.5-MoE-A2.7B
Input Output 
Input Format:
Not specified
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Gradient checkpointing: enabled, Flash attention: enabled
LLM NameQwen1.5 MoE A2.7B Wikihow
Repository 🤗https://huggingface.co/MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow 
Base Model(s)  Qwen/Qwen1.5-MoE-A2.7B   Qwen/Qwen1.5-MoE-A2.7B
Model Size14.3b
Required VRAM28.7 GB
Updated2025-10-14
MaintainerMaziyarPanahi
Model Typeqwen2_moe
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.7 GB: 6-of-6
Model ArchitectureQwen2MoeForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 MoE A2.7B Wikihow

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 MoE A2.7B Chat32K / 28.7 GB31679125
Qwen1.5 MoE A2.7B8K / 28.7 GB45602207
...Aux Free Sft Math7k 1e 3 Gamma8K / 28.7 GB4421
Qwen1.5 MoE Sft Math7k8K / 57.3 GB1951
Note: green Score (e.g. "73.2") means that the model is better than MaziyarPanahi/Qwen1.5-MoE-A2.7B-Wikihow.

Rank the Qwen1.5 MoE A2.7B Wikihow 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? 51545 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