Falcon2 5.5B Spanish is an open-source language model by ssmits. Features: 11b LLM, VRAM: 10.9GB, Context: 8K, License: apache-2.0, Merged, LLM Explorer Score: 0.14.
Will not generalize appropriately to non-supported languages, Carries web stereotypes and biases
Additional Notes
Pruning done based on layer similarity analysis to maintain performance while reducing model size.
Supported Languages
English (high), German (high), Spanish (high), French (high), Italian (high), Portuguese (high), Polish (high), Dutch (high), Romanian (high), Czech (high), Swedish (high)
Training Details
Data Sources:
wikimedia/wikipedia Spanish (es) subset
Data Volume:
5T tokens, ~1B of continued pre-training (~1M rows of 1k tokens)
Methodology:
mergekit
Context Length:
1000
Responsible Ai Considerations
Fairness:
Falcon2-5.5B may reflect web stereotypes and biases.
Mitigation Strategies:
Finetuning for specific tasks; guardrails for production use.
Note: green Score (e.g. "73.2") means that the model is better than ssmits/Falcon2-5.5B-Spanish.
Rank the Falcon2 5.5B Spanish Capabilities
๐ 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! ๐
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.