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

WizardLM 30B Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  WizardLM 30B Fp16   URL Share it on

  2058   
  Autotrain compatible   Fp16   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TheBloke/WizardLM-30B-fp16 

WizardLM 30B Fp16 Benchmarks

ARC: 62.54 vs 96.7 (so35)-35.3%
HellaSwag: 83.28 vs 95.3 (gpt4)-12.6%
MMLU: 59.03 vs 88.3 (so35)-33.1%
TruthfulQA: 52.49 vs 59 (gpt4)-11%
WinoGrande: 77.51 vs 87.5 (gpt4)-11.4%
GSM8K: 22.21 vs 96.4 (so35)-77%
LLME Score: 0.1467
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
WizardLM 30B Fp16 (TheBloke/WizardLM-30B-fp16)

WizardLM 30B Fp16 Parameters and Internals

Model Type 
text generation
Additional Notes 
The model was created by merging a delta with the Llama 30B model.
Input Output 
Input Format:
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: prompt goes here ASSISTANT:
Accepted Modalities:
text
Output Format:
text response
LLM NameWizardLM 30B Fp16
Repository 🤗https://huggingface.co/TheBloke/WizardLM-30B-fp16 
Model Size30b
Required VRAM65.2 GB
Updated2025-02-22
MaintainerTheBloke
Model Typellama
Model Files  9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to WizardLM 30B Fp16

Best Alternatives
Context / RAM
Downloads
Likes
Tenebra 30B Alpha01 FP1616K / 65 GB17928
Tenebra 30B Alpha01 4BIT16K / 19.4 GB18961
...nebra 30B Alpha01 EXL2 2 80bpw16K / 11.9 GB121
Tenebra 30B Alpha01 EXL2 3bpw16K / 12.7 GB110
...nebra 30B Alpha01 EXL2 2 50bpw16K / 10.7 GB60
Tenebra 30B Alpha01 3BIT16K / 12.9 GB90
... 30B Supercot SuperHOT 8K Fp168K / 65.2 GB20724
Platypus 30B SuperHOT 8K Fp168K / 65.2 GB20712
GPlatty 30B SuperHOT 8K Fp168K / 65.2 GB20611
Tulu 30B Fp162K / 65.2 GB20575
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/WizardLM-30B-fp16.

Rank the WizardLM 30B Fp16 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? 43470 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