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

H2o Danube2 1.8B Sft by h2oai

 »  All LLMs  »  h2oai  »  H2o Danube2 1.8B Sft   URL Share it on

  120   

H2o Danube2 1.8B Sft is an open-source language model by h2oai. Features: 1.8b LLM, VRAM: 3.7GB, Context: 8K, License: apache-2.0, HF Score: 47.4, LLM Explorer Score: 0.16, Arc: 42.7, HellaSwag: 72.8, MMLU: 35.9, TruthfulQA: 38.7, WinoGrande: 68.5, GSM8K: 25.6.

  Arxiv:2401.16818   Conversational   En   Endpoints compatible   Gpt   H2o-llmstudio   Mistral   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/h2oai/h2o-danube2-1.8b-sft 

H2o Danube2 1.8B Sft Benchmarks

ARC: 42.66 vs 96.7 (so35)-55.9%
HellaSwag: 72.75 vs 95.3 (gpt4)-23.7%
MMLU: 35.9 vs 88.3 (so35)-59.3%
TruthfulQA: 38.7 vs 59 (gpt4)-34.4%
WinoGrande: 68.51 vs 87.5 (gpt4)-21.7%
GSM8K: 25.63 vs 96.4 (so35)-73.4%
LLME Score: 0.16188
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
H2o Danube2 1.8B Sft (h2oai/h2o-danube2-1.8b-sft)
🌟 Advertise your project 🚀

H2o Danube2 1.8B Sft Parameters and Internals

Model Type 
chat, fine-tuned
Additional Notes 
The model is adjusted from Llama 2 architecture, using the Transformers library for deployment.
Training Details 
Methodology:
fine-tuning with SFT (Supervised Fine-Tuning)
Context Length:
8192
Model Architecture:
Mistral model with Mistral tokenizer
Input Output 
Input Format:
text with HF Tokenizer chat template
Accepted Modalities:
text
Output Format:
text
LLM NameH2o Danube2 1.8B Sft
Repository 🤗https://huggingface.co/h2oai/h2o-danube2-1.8b-sft 
Model Size1.8b
Required VRAM3.7 GB
Updated2026-04-09
Maintainerh2oai
Model Typemistral
Model Files  3.7 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to H2o Danube2 1.8B Sft

Best Alternatives
Context / RAM
Downloads
Likes
H2o Danube 1.8B Chat16K / 3.7 GB14955
H2o Danube 1.8B Base16K / 3.7 GB16243
Cypher Mini 1.8B16K / 3.7 GB1112
H2o Danube 1.8B Sft16K / 3.7 GB10711
PixieZehirNano16K / 3.7 GB100
Cypher CoT 1.8B16K / 3.7 GB121
...1.8B Chat Sft Merge Fourier V116K / 7.3 GB51
H2o Danube2 1.8B Chat8K / 3.7 GB38762
H2o Danube2 1.8B Base8K / 3.7 GB40447
Binary Clumsy Bear8K / 7.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2o-danube2-1.8b-sft.

Rank the H2o Danube2 1.8B Sft 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer