---
license: apache-2.0
datasets:
- m-a-p/COIG-CQIA
---

# llama3-8B-lima

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

SFT with m-a-p/COIG-CQIA. 2 epoch qlora. Code under [https://huggingface.co/HenryJJ/llama3-8B-lima/blob/main/config/llama3-cqia.yml](https://huggingface.co/HenryJJ/llama3-8B-lima/blob/main/config/llama3-llama3-cqia.yml).

# Model Details
* **Trained by**: trained by HenryJJ.
* **Model type:**  **llama3** is an auto-regressive language model based on the Llama 3 transformer architecture.
* **Language(s)**: English
* **License for llama3-8B-lima**: apache-2.0 license


# Prompting

Prompt format chatml:
This model uses ChatML prompt format. 
```
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

```

Example:
```
<|im_start|>system
You are a helpful assistant.
<|im_start|>user
who is the president of us
<|im_start|>assistant
```