|
--- |
|
license: mit |
|
datasets: |
|
- Open-Orca/SlimOrca-Dedup |
|
- migtissera/Synthia-v1.3 |
|
- LDJnr/Verified-Camel |
|
- LDJnr/Pure-Dove |
|
- LDJnr/Capybara |
|
- meta-math/MetaMathQA |
|
- Intel/orca_dpo_pairs |
|
- argilla/ultrafeedback-binarized-preferences-cleaned |
|
--- |
|
 |
|
|
|
# Phi-2 Orange Version 2 |
|
|
|
A two-step finetune of Phi-2, with a bit more zest. |
|
|
|
First using a collection of broad training data: |
|
|
|
- [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup) |
|
- [migtissera/Synthia-v1.3](https://huggingface.co/datasets/migtissera/Synthia-v1.3) |
|
- [LDJnr/Verified-Camel](https://huggingface.co/datasets/LDJnr/Verified-Camel) |
|
- [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove) |
|
- [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara) |
|
- [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA) |
|
|
|
And then a DPO finetune using: |
|
|
|
- [Intel/orca_dpo_pairs](https://huggingface.co/datasets/Intel/orca_dpo_pairs) |
|
- [argilla/ultrafeedback-binarized-preferences-cleaned](https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned) |
|
|
|
|
|
# Prompt Format |
|
|
|
Phi-2 Orange uses ChatML as the prompt format, with or without the system instruction. |
|
|
|
To 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 |
|
|
|
``` |
|
|
|
You can also omit the system prompt if you wish: |
|
|
|
``` |
|
<|im_start|>user |
|
Why is the sky blue?<|im_end|> |
|
<|im_start|>assistant |
|
|
|
``` |
|
|
|
|
