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

H2o Danube 1.8B Base by h2oai

 »  All LLMs  »  h2oai  »  H2o Danube 1.8B Base   URL Share it on

  759   
  Arxiv:2401.16818   Autotrain compatible   En   Endpoints compatible   Gpt   Mistral   Region:us   Safetensors

H2o Danube 1.8B Base Benchmarks

ARC: 39.42 vs 96.7 (so35)-59.2%
HellaSwag: 69.58 vs 95.3 (gpt4)-27%
MMLU: 25.94 vs 88.3 (so35)-70.6%
TruthfulQA: 33.86 vs 59 (gpt4)-42.6%
WinoGrande: 64.48 vs 87.5 (gpt4)-26.3%
GSM8K: 1.44 vs 96.4 (so35)-98.5%
LLME Score: 0.25574
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

H2o Danube 1.8B Base Parameters and Internals

LLM NameH2o Danube 1.8B Base
Repository 🤗https://huggingface.co/h2oai/h2o-danube-1.8b-base 
Model Size1.8b
Required VRAM3.7 GB
Updated2024-09-07
Maintainerh2oai
Model Typemistral
Model Files  3.7 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16
H2o Danube 1.8B Base (h2oai/h2o-danube-1.8b-base)

Best Alternatives to H2o Danube 1.8B Base

Best Alternatives
Context / RAM
Downloads
Likes
H2o Danube 1.8B Chat16K / 3.7 GB403355
Cypher Mini 1.8B16K / 3.7 GB642
H2o Danube 1.8B Sft16K / 3.7 GB26311
PixieZehirNano16K / 3.7 GB120
Cypher CoT 1.8B16K / 3.7 GB91
...1.8B Chat Sft Merge Fourier V116K / 7.3 GB101
H2o Danube2 1.8B Chat8K / 3.7 GB733455
H2o Danube2 1.8B Sft8K / 3.7 GB34626
H2o Danube2 1.8B Base8K / 3.7 GB110243
Binary Clumsy Bear8K / 7.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2o-danube-1.8b-base.

Rank the H2o Danube 1.8B Base 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? 35693 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 v2024072803
  Support LLM Explorer