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

H2o Danube3 4B Base by h2oai

 »  All LLMs  »  h2oai  »  H2o Danube3 4B Base   URL Share it on

  742   
  Arxiv:2407.09276   Autotrain compatible   En   Endpoints compatible   Gpt   H2o-llmstudio   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/h2oai/h2o-danube3-4b-base 

H2o Danube3 4B Base Benchmarks

MMLU Pro: 12.33
GPQA: 5.48
MUSR: 6.53
BBH: 10.56
IFEval: 23.38 vs 88 (so35)-73.4%
MATH Lvl 5: 2.27
LLME Score: 0.22713
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
H2o Danube3 4B Base (h2oai/h2o-danube3-4b-base)

H2o Danube3 4B Base Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Models can be quantized to 8-bit or 4-bit and support sharding across multiple GPUs.
Training Details 
Context Length:
8192
Model Architecture:
Adjusted Llama 2 with Mistral tokenizer, 24 layers, 32 heads, 8 query groups
LLM NameH2o Danube3 4B Base
Repository 🤗https://huggingface.co/h2oai/h2o-danube3-4b-base 
Model Size4b
Required VRAM8 GB
Updated2025-06-01
Maintainerh2oai
Model Typellama
Model Files  5.0 GB: 1-of-2   3.0 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.42.3
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to H2o Danube3 4B Base

Best Alternatives
Context / RAM
Downloads
Likes
Xgen Small 4B Instruct R256K / 17.7 GB402
SJT 4B146K / 7.6 GB110
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB833469
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB3654
Loxa 4B128K / 16 GB860
Nemotron W 4b MagLight 0.1128K / 9.2 GB133
Nemotron W 4b Halo 0.1128K / 9.2 GB173
...ama 3.1 Minitron 4B Depth Base128K / 9.1 GB742221
CharGen V3 Mini128K / 9 GB144
Aura 4B128K / 9 GB711
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2o-danube3-4b-base.

Rank the H2o Danube3 4B 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? 47770 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