Commit
•
c568bc0
1
Parent(s):
b3ad63b
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
|
3 |
+
---
|
4 |
+
base_model: meta-llama/Meta-Llama-3-70B
|
5 |
+
tags:
|
6 |
+
- llama-3
|
7 |
+
- instruct
|
8 |
+
- finetune
|
9 |
+
- synthetic data
|
10 |
+
- distillation
|
11 |
+
model-index:
|
12 |
+
- name: Wizard-llama3-70B
|
13 |
+
results: []
|
14 |
+
license: mit
|
15 |
+
language:
|
16 |
+
- en
|
17 |
+
---
|
18 |
+
|
19 |
+
# Wizard-llama3-70B
|
20 |
+
|
21 |
+
|
22 |
+
![1704515374925127s.jpg](https://cdn-uploads.huggingface.co/production/uploads/65d1f383351255ba48a4f831/3thSAFgTeV1C275uuik54.jpeg)
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
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.
|
27 |
+
|
28 |
+
Wizard-llama3-70B has a variety of instruction, logic and coding skills. It also has initial agentic abilities and supports function calling.
|
29 |
+
|
30 |
+
tried to make the model as uncensored as possible .
|
31 |
+
|