Quantized models available from TheBloke: GGML and GPTQ versions.
Supported Languages
en (proficient)
Training Details
Methodology:
Using a highly experimental tensor type merge technique. Each layer composed of several tensors, each with a unique ratio applied, with involvement of gradients to finetune behavior.
Input Output
Input Format:
Based on Alpaca formatting. Instruction format: ### Instruction: {Your instruction or question}. ### Response:
Note: green Score (e.g. "73.2") means that the model is better than WendyHoang/roleplay-model.
Rank the Roleplay Model 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? 52394 in total.