llama3-8b-cqia
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.
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
- Downloads last month
- 15
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.