The provided files are in Replit GGML format and not compatible with llama.cpp or related tools. They are compatible with KoboldCpp, LM Studio, LoLLMs-WebUI, ctransformers, rustformers' llm, and the ggml-replit binary.
Input Output
Performance Tips:
Using GPU offloading can reduce RAM usage and increase performance.
Release Notes
Version:
v1.3b
Notes:
Model finetuned on Open-Orca/OpenOrca. Available in multiple quantized formats for different use cases.
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/replit-openorca-GGML.
Rank the Replit Openorca GGML Capabilities
🆘 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! 🌟
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? 53972 in total.