Downloads · 30 days
0
JunchengXie/Llama-2-13b-hf-gpt-4-80k
Llama-2-13b-hf-gpt-4-80k is a machine learning model from JunchengXie. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This model is finetuned on the distillation data from GPT-4. The base model is meta-llama/Llama-2-13b-hf The model has a query format as in llama-2.
Downloads · 30 days
0
Access
Public
Updated Mar 13, 2024
Repo size
500 KB
Likes
0
Public
Click a slice to open those files.
.json1.8 MB · 79%
From the Hugging Face model README
This model is finetuned on the distillation data from GPT-4. The base model is meta-llama/Llama-2-13b-hf
The model has a query format as in llama-2.
<s> [INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>
{query} [/INST]