Not a state-of-the-art model, Experimental model, Can exhibit undesired behaviors: factual inaccuracies, biases, offensive responses, toxicity, and hallucinations
Considerations:
Exercise good judgment when applying this technology.
Additional Notes
Model not suitable for environments other than research purposes.
Supported Languages
EN (English)
Training Details
Data Sources:
tatsu-lab/alpaca
Data Volume:
50k records
Methodology:
Fine-tuning on GPT-2
Hardware Used:
Single T4 GPU
Model Architecture:
Derived from GPT-2
Input Output
Performance Tips:
Including `torch_dtype=torch.bfloat16` is generally recommended to reduce memory usage.
Note: green Score (e.g. "73.2") means that the model is better than aisquared/dlite-v1-124m.
Rank the Dlite V1 124M 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? 52758 in total.