Task vector optimization approach was adjusted due to slightly higher training loss, leading to a merging and retraining plan to achieve desired performance with reduced parameters.
Supported Languages
en (proficient)
Training Details
Data Sources:
netcat420/MFANN
Methodology:
Task vector optimization using DARE-TIES to reduce parameters, followed by a merging strategy with the last version using TIES alone.
Note: green Score (e.g. "73.2") means that the model is better than netcat420/MFANN3bv0.16.11.
Rank the MFANN3bv0.16.11 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.