phi-2-orange-v2

Phi-2 Orange Version 2

A two-step finetune of Phi-2, with a bit more zest.

This is an improved version of the original Phi-2-Orange that uses an updated training process on the same datasets.

It also uses the latest updated model from Microsoft's Phi-2, making it directly usable within Hugging Face's Transformers library (without the need for trust remote code).

Prompt Format

Phi-2 Orange v2 uses ChatML as the prompt format.
(Update 12th March 2024: fixed eos_token issue)

It's recommended to always prompt with a system instruction (use whatever system prompt you like):

<|im_start|>system
You are a helpful assistant for Python which outputs in Markdown format.<|im_end|>
<|im_start|>user
Write a function to calculate the Fibonacci sequence<|im_end|>
<|im_start|>assistant

For example, if you find the model's output to be overly verbose, instruct it to be short and concise:

<|im_start|>system
You are a helpful assistant. Be short and direct in your answers.<|im_end|>
<|im_start|>user
Was Tom Hanks in the movie Forrest Gump? If so, who did he play and give details of the plot.<|im_end|>
<|im_start|>assistant

Evaluations

Open LLM Leaderboard Evaluation Results
Detailed results can be found here

YALL - Yet Another LLM Leaderboard
Evaluation from mlabonne's alternative LLM leaderboard:

Limitations

This model shares the same limitations as the underlying Phi-2 model, details of which are found here.