FLOR 6.3B Instructed by projecte-aina

 ยป  All LLMs  ยป  projecte-aina  ยป  FLOR 6.3B Instructed   URL Share it on

  Autotrain compatible   Bloom   Endpoints compatible   License:apache-2.0   Region:us   Safetensors   Sharded   Tensorflow

FLOR 6.3B Instructed Parameters and Internals

Model Type 
transformer-based, causal language model
Use Cases 
Primary Use Cases:
text-generation tasks, summarization, Question Answering, creative writing
Limitations:
Potential bias and toxicity
Considerations:
Users should mitigate risks and comply with applicable regulations.
Additional Notes 
No specific bias and toxicity measures have been taken yet, research is intended in the future.
Supported Languages 
Catalan (good), Spanish (good), English (good)
Training Details 
Data Sources:
InstruCat, Dolly dataset, MENTOR_ES, MENTOR_CA
Data Volume:
140B tokens
Methodology:
Language adaptation technique; continuous pre-training
Model Architecture:
Transformer-based
Safety Evaluation 
Ethical Considerations:
The model may be biased due to the nature of the training data derived from web sources.
LLM NameFLOR 6.3B Instructed
Repository ๐Ÿค—https://huggingface.co/projecte-aina/FLOR-6.3B-Instructed 
Model Size6.3b
Required VRAM12.4 GB
Updated2024-07-04
Maintainerprojecte-aina
Model Typebloom
Model Files  9.9 GB: 1-of-2   2.5 GB: 2-of-2
Model ArchitectureBloomForCausalLM
Licenseapache-2.0
Transformers Version4.28.1
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50257
Torch Data Typefloat16
Errorsreplace

Best Alternatives to FLOR 6.3B Instructed

Best Alternatives
Context / RAM
Downloads
Likes
OpenHermes 2.5 FLOR 6.3B0K / 13 GB311
FLOR 6.3B Xat0K / 12.5 GB250
FLOR RAG EADOP0K / 12.4 GB210
FlorRAG0K / 12.4 GB00
FLOR 6.3B0K / 12.5 GB00
Note: green Score (e.g. "73.2") means that the model is better than projecte-aina/FLOR-6.3B-Instructed.

Rank the FLOR 6.3B Instructed Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227