Views
No views yet
microsoft/phi-2 model fine-tuned using QLoRA to explain complex topics in simple, ELI5-style terms.Instruct: <your question>\nOutput:.llama.cpp.Q4_K_M is recommended for general use.llama.cpp:
./llama-cli -m ./ExplainIt-Phi-Q4_K_M.gguf -p "Instruct: Why is the sky blue?\nOutput:" -n 256| File Name | Quantization | Use Case |
|---|---|---|
ExplainIt-Phi-Q4_K_M.gguf | Q4_K_M (4-bit) | Default. Balanced quality and size. |
ExplainIt-Phi-Q5_K_M.gguf | Q5_K_M (5-bit) | Higher quality for systems with more RAM. |
ExplainIt-Phi-Q8_0.gguf | Q8_0 (8-bit) | Near-lossless, best for GPU execution. |
What is an API and what does it do, in simple terms?| Base Phi-2 Model (Before) | Fine-Tuned ExplainIt-Phi (After) |
|---|---|
| "An API, or Application Programming Interface, is a set of rules and protocols that allows different software applications to communicate with each other. It acts as a bridge between two applications, allowing them to exchange data and functionality." | "An API is like a waiter in a restaurant. You (an application) don't need to know how the kitchen works. You just give your order (a request) to the waiter (the API), and the waiter brings you your food (the data)." |
sentence-transformers/eli5 dataset. For a full breakdown of the training procedure, hyperparameters, and infrastructure, please see the project's GitHub repository.