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

WizardLM 2 4x7B MoE EXL2 3 0bpw by Skylaude

 »  All LLMs  »  Skylaude  »  WizardLM 2 4x7B MoE EXL2 3 0bpw   URL Share it on

  12   
  3-bit   Autotrain compatible   Endpoints compatible   Exl2   Merge   Mergekit   Microsoft/wizardlm-2-7b   Mistral   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-3_0bpw 

WizardLM 2 4x7B MoE EXL2 3 0bpw Benchmarks

LLME Score: 0.19046
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WizardLM 2 4x7B MoE EXL2 3 0bpw (Skylaude/WizardLM-2-4x7B-MoE-exl2-3_0bpw)

WizardLM 2 4x7B MoE EXL2 3 0bpw Parameters and Internals

Model Type 
MoE
Additional Notes 
Quantized using version 0.0.18 of ExLlamaV2. Recommended to set experts per token to 4 for best results. Context length should be the same as Mistral-7B-Instruct-v0.1 (8k tokens). Vicuna-v1.1 is recommended for instruction templates.
Training Details 
Methodology:
Quantization using ExLlamaV2 version 0.0.18
Context Length:
8000
LLM NameWizardLM 2 4x7B MoE EXL2 3 0bpw
Repository 🤗https://huggingface.co/Skylaude/WizardLM-2-4x7B-MoE-exl2-3_0bpw 
Model Size7b
Required VRAM9.4 GB
Updated2024-12-22
MaintainerSkylaude
Model Typemixtral
Model Files  8.6 GB: 1-of-2   0.8 GB: 2-of-2
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to WizardLM 2 4x7B MoE EXL2 3 0bpw

Best Alternatives
Context / RAM
Downloads
Likes
Buttercup 4x7B 6bpw EXL232K / 18.4 GB122
BurningBruce 003 EXL2 B8.032K / 24.3 GB131
...ixtral 2x7b DPO 8.0bpw H8 EXL232K / 13 GB164
...ixtral 2x7b DPO 4.0bpw H6 EXL232K / 6.7 GB211
...ixtral 2x7b DPO 6.0bpw H6 EXL232K / 9.8 GB191
...ixtral 2x7b DPO 5.0bpw H6 EXL232K / 8.3 GB151
...t V0.2 2x7B MoE 6.0bpw H6 EXL232K / 9.9 GB101
...iveFusion 4x7b MoE EXL2 3.5BPW8K / 10.8 GB141
...lue Orchid 2x7b 8.0bpw H8 EXL28K / 13 GB425
...lue Orchid 2x7b 5.0bpw H6 EXL28K / 8.2 GB274

Rank the WizardLM 2 4x7B MoE EXL2 3 0bpw 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? 40066 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