File size: 802 Bytes
c94c500
 
 
6e39873
f202f82
 
 
 
c94c500
c5af895
 
 
 
 
 
 
 
 
a35bfef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
---
license: other
license_name: llama-3
license_link: https://llama.meta.com/llama3/license/
tags:
- llama-3
- dolphin
- gguf
---
The GGUF files of [RDson/Dolphin-less-Llama-3-Instruct-8B](https://huggingface.co/RDson/Dolphin-less-Llama-3-Instruct-8B).

Use the ChatML prompt template
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Or as Ollama Modelfile
```
FROM Dolphin-less-Llama-3-Instruct-8B-GGUF-Q<PICK A FILE HERE>.gguf
TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
{{ .Response }}<|im_end|>"""
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
SYSTEM "You are Dolphin, a helpful AI assistant."
```
Whichever works for you...