File size: 1,175 Bytes
8b839d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8252704
083cfe0
 
8252704
8b839d3
 
 
 
7e8a506
8b839d3
 
 
 
 
 
 
 
 
 
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

---
license: other
license_name: yi-license
license_link: LICENSE
datasets:
- totally-not-an-llm/EverythingLM-data-V3
pipeline_tag: text-generation
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/4OQkvAa1zOK4Devv-aUdL.png)

The perfect organism. 

An adapter for KnutJaegersberg/Yi-34B-Llamafied. 5 epochs with NEFTune. 
The brand new bitsandbytes 4-bit file format. 

Run pip install -U bitsandbytes
and install this pull requested transformer version: 
https://github.com/poedator/transformers/tree/save4

Might still be buggy. 
It was a bit too early. 
I'll wait until the functionality is officially supported, due to some cuda issues. I don't want to resolve those, I'll just wait a couple of days. 

Prompt Example:
```
### System:

You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.

### Instruction: 

How do you fine tune a large language model? 

### Response:
```


![image/png](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/8KYMW1KGzyE19GWxSTG7m.png)