---
datasets:
- raincandy-u/Dextromethorphan-50k-v0.1
library_name: transformers
pipeline_tag: text-generation
license: mit
---


![image/png](https://cdn-uploads.huggingface.co/production/uploads/657eb5b256c9c67605a6e8b5/f96pPiJQb3puzbPYNknG2.png)

# phillama-3.8b-v1

Phillama is a model based on Phi-3-mini and trained on Llama-generated datasets to make it more "llama-like".

Also, this model is converted into Llama format, so it will work with any Llama-2/3 workflow.

# Dataset

|     Source      |   Task   | Number of examples（k） |
| :-----------: | :------: | :--------------: |
|   lmsys-1m    | Chat |        50        |
| dolphin-coder |   Code   |        10        |
|   slimorca    | Reasoning |        10        |

<h1>For more information include training details, see <a href="https://angelkawaii.xyz/2024/04/26/llama-3-finetune-1/">this blog post</a></h1>

# System prompt

`You are a humanoid AI assistant. You think step by step and give detailed long response.`

# Prompt template

```
<|system|>
You are a humanoid AI assistant. You think step by step and give detailed long response.<|end|>
<|user|>
Why people like llama?<|end|>
<|assistant|>
```