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

Falcon2 5.5B Danish by ssmits

 »  All LLMs  »  ssmits  »  Falcon2 5.5B Danish   URL Share it on

  15   
  Merged Model   Autotrain compatible Base model:finetune:tiiuae/fal...   Base model:tiiuae/falcon-11b   Conversational   Custom code   Da   Endpoints compatible   Falcon   Region:us   Safetensors   Sharded   Tensorflow   Tiiuae/falcon-11b
Model Card on HF 🤗: https://huggingface.co/ssmits/Falcon2-5.5B-Danish 

Falcon2 5.5B Danish Benchmarks

LLME Score: 0.187
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Falcon2 5.5B Danish (ssmits/Falcon2-5.5B-Danish)

Falcon2 5.5B Danish Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, foundation for further specialization, fine-tuning
Applications:
summarization, text generation, chatbot
Primary Use Cases:
Quantum computing concept explanation
Limitations:
limited generalization to non-model-specific languages
Considerations:
Requires adequate assessment and mitigation of risks for production use.
Additional Notes 
The merge method ensures layer similarity with Danish text inputs.
Supported Languages 
da (primary), en (limited), de (limited), es (limited), fr (limited), it (limited), pt (limited), pl (limited), nl (limited), ro (limited), cs (limited), sv (limited)
Training Details 
Data Sources:
wikimedia/wikipedia Danish subset
Data Volume:
5T tokens
Methodology:
Continued pre-training with pruning strategy using PruneMe
Model Architecture:
Pruned model layers [0, 25] and [56, 59] undergo passthrough merge method
Responsible Ai Considerations 
Fairness:
The model may carry stereotypes and biases encountered online.
Mitigation Strategies:
Recommend finetuning for specific tasks and precautions in production use.
Input Output 
Input Format:
text prompt
Accepted Modalities:
text
Output Format:
generated text
Performance Tips:
Use finetuning and specify tasks of interest.
LLM NameFalcon2 5.5B Danish
Repository 🤗https://huggingface.co/ssmits/Falcon2-5.5B-Danish 
Base Model(s)  Falcon 11B   tiiuae/falcon-11B
Merged ModelYes
Model Size11b
Required VRAM10.9 GB
Updated2025-02-22
Maintainerssmits
Model Typefalcon
Model Files  0.9 GB: 1-of-12   1.0 GB: 2-of-12   0.9 GB: 3-of-12   0.9 GB: 4-of-12   1.0 GB: 5-of-12   0.9 GB: 6-of-12   0.9 GB: 7-of-12   1.0 GB: 8-of-12   0.9 GB: 9-of-12   0.9 GB: 10-of-12   1.0 GB: 11-of-12   0.6 GB: 12-of-12
Supported Languagesda
Model ArchitectureFalconForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to Falcon2 5.5B Danish

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 11B8K / 22.1 GB31645212
Falcon2 5.5B Multilingual8K / 10.9 GB2144
Falcon2 5.5B Polish8K / 10.9 GB14941
Falcon2 5.5B Portuguese8K / 10.9 GB2040
Falcon2 11B8K / 6.6 GB520
Enron Falcon 11B8K / 7.6 GB141
Falcon2 5.5B Dutch8K / 10.9 GB791
Falcon2 5.5B Italian8K / 10.9 GB640
Falcon2 5.5B German8K / 10.9 GB350
Falcon2 5.5B Czech8K / 10.9 GB280
Note: green Score (e.g. "73.2") means that the model is better than ssmits/Falcon2-5.5B-Danish.

Rank the Falcon2 5.5B Danish 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