File size: 668 Bytes
b831cda
 
 
5c5c897
 
 
 
 
8390881
 
 
 
74a4098
8390881
5c5c897
 
 
550d2f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5c5c897
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
34
35
36
37
38
39
40
41
---
license: mit
---

Base Mode: Llama 7B

Llama DEUS v3 is the largest dataset I've trained on yet, including:

GPTeacher - General Instruct - Code Instruct - Roleplay Instruct  
My unreleased Roleplay V2 Instruct  
GPT4-LLM Uncensored + Unnatural Instructions  
WizardLM Uncensored  
CamelAI's 20k Biology, 20k Physics, 20k Chemistry, and 50k Math GPT4 Datasets  
CodeAlpaca  

This model was trained for 4 epochs over 1 day of training, it's a rank 128 LORA that targets attention heads, LM_Head, and MLP layers

Prompt format:

```
### Instruction:
<prompt>
  
### Response:
  
```

or

```
### Instruction:
<prompt>

### Input:
<input>
  
### Response:
  
```