---
base_model: meta-llama/Meta-Llama-3-70B
tags:
- llama-3
- instruct
- finetune
- synthetic data
- distillation
model-index:
- name: Wizard-llama3-70B
  results: []
license: mit
language:
- en
---

# Wizard-llama3-70B



![image.png](https://cdn-uploads.huggingface.co/production/uploads/65d1f383351255ba48a4f831/QofRmu_JA6ftPX0qmvt3P.png)

## Model description

Wizard-llama3-70B is the fine tune of llama3 70b on top of public datasets and some additional code datasets. model uses ChatML prompt template format.

Wizard-llama3-70B has a variety of instruction, logic  and coding skills. It also has initial agentic abilities and supports function calling.

tried to make the model as uncensored as possible .