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 Sft by h2oai

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

  440   
  Arxiv:2401.16818   Autotrain compatible   Conversational Dataset:huggingfaceh4/ultracha...   Dataset:meta-math/metamathqa   Dataset:open-orca/openorca   Dataset:openassistant/oasst2   En   Endpoints compatible   Gpt   H2o-llmstudio   Mistral   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/h2oai/h2o-danube-1.8b-sft 

H2o Danube 1.8B Sft Benchmarks

ARC: 40.19 vs 96.7 (so35)-58.4%
HellaSwag: 67.34 vs 95.3 (gpt4)-29.3%
MMLU: 33.75 vs 88.3 (so35)-61.8%
TruthfulQA: 40.29 vs 59 (gpt4)-31.7%
WinoGrande: 65.43 vs 87.5 (gpt4)-25.2%
GSM8K: 15.09 vs 96.4 (so35)-84.3%
LLME Score: 0.2181
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 Sft (h2oai/h2o-danube-1.8b-sft)

H2o Danube 1.8B Sft Parameters and Internals

Model Type 
chat, fine-tuned
Use Cases 
Areas:
Research, Commercial applications
Limitations:
Incorrect, nonsensical or irrelevant responses
Considerations:
Users should ensure ethical use and be aware of potential biases in the generated outputs.
Additional Notes 
The model architecture details and usage guidelines are provided in the model card and technical report.
Training Details 
Data Sources:
Open-Orca/OpenOrca, OpenAssistant/oasst2, HuggingFaceH4/ultrachat_200k, meta-math/MetaMathQA
Methodology:
The model was trained using H2O LLM Studio with sliding window attention from mistral.
Context Length:
16384
Model Architecture:
MistralForCausalLM incorporating Llama 2 architecture with sliding window attention.
Input Output 
Performance Tips:
Quantization and sharding are supported in the transformers library for efficient usage.
LLM NameH2o Danube 1.8B Sft
Repository 🤗https://huggingface.co/h2oai/h2o-danube-1.8b-sft 
Model Size1.8b
Required VRAM3.7 GB
Updated2024-12-26
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
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to H2o Danube 1.8B Sft

Best Alternatives
Context / RAM
Downloads
Likes
H2o Danube 1.8B Chat16K / 3.7 GB242654
H2o Danube 1.8B Base16K / 3.7 GB123042
Cypher Mini 1.8B16K / 3.7 GB982
PixieZehirNano16K / 3.7 GB100
Cypher CoT 1.8B16K / 3.7 GB171
...1.8B Chat Sft Merge Fourier V116K / 7.3 GB81
H2o Danube2 1.8B Chat8K / 3.7 GB296660
H2o Danube2 1.8B Base8K / 3.7 GB161646
H2o Danube2 1.8B Sft8K / 3.7 GB3936
Binary Clumsy Bear8K / 7.3 GB100
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2o-danube-1.8b-sft.

Rank the H2o Danube 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? 40248 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