LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2idae 16x14B V1.0 by hywu

 »  All LLMs  »  hywu  »  Qwen2idae 16x14B V1.0   URL Share it on

  11   
  Arxiv:1902.00751   Arxiv:2212.05055   Arxiv:2305.14314   Arxiv:2401.02731   Autotrain compatible   Conversational   Custom code Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss...   Dataset:meta-math/metamathqa   Dataset:open-orca/slimorca   En   Endpoints compatible   Instruct   Moe   Qwen2idae   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0 

Qwen2idae 16x14B V1.0 Benchmarks

LLME Score: 0.18314
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2idae 16x14B V1.0 (hywu/Qwen2idae-16x14B-v1.0)

Qwen2idae 16x14B V1.0 Parameters and Internals

Model Type 
text generation
Additional Notes 
Part of Parameter-Efficient Sparsity Crafting project in collaboration with Serp-ai.
Supported Languages 
English (-)
Training Details 
Data Sources:
Open-Orca/SlimOrca, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, meta-math/MetaMathQA
Methodology:
Parameter-Efficient Sparsity Crafting, Instruction Tuning, MoE structure, QLoRA, Adapter techniques, Efficient Sparse Upcycling
Hardware Used:
unsloth support
Model Architecture:
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts
Input Output 
Input Format:
Expecting tokenized input with special tokens for context separation.
Accepted Modalities:
text
Output Format:
Text
Release Notes 
Version:
v1.0
Date:
3/12/2024
Notes:
Qwen2idae-16x14B-v1.0 released.
LLM NameQwen2idae 16x14B V1.0
Repository 🤗https://huggingface.co/hywu/Qwen2idae-16x14B-v1.0 
Model Size17.5b
Required VRAM35.1 GB
Updated2024-12-21
Maintainerhywu
Model Typeqwen2idae
Instruction-BasedYes
Model Files  5.0 GB: 1-of-8   4.9 GB: 2-of-8   4.9 GB: 3-of-8   5.0 GB: 4-of-8   5.0 GB: 5-of-8   4.9 GB: 6-of-8   3.8 GB: 7-of-8   1.6 GB: 8-of-8
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Rank the Qwen2idae 16x14B V1.0 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? 40013 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 v20241217
  Support LLM Explorer