metadata
license: apache-2.0
datasets:
- 64bits/lima_vicuna_format
llama3-8B-lima
SFT with 64bits/lima_vicuna_format. 3 epoch qlora. Code under https://huggingface.co/HenryJJ/llama3-8B-lima/blob/main/config/llama3-lima.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