Downloads · 30 days
13
10% of all-time downloads
Deacon-34b-4bit
KnutJaegersberg/Deacon-34b-4bit
Deacon-34b-4bit is a text generation model from KnutJaegersberg. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
All-time downloads
126
Public
Repo size
28.1 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin18.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Nov 9, 2023
- Updated
- Dec 3, 2023
- SHA
- 7e8a5062
Try a prompt
Model card
From the Hugging Face model README
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:
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Created
- Nov 9, 2023
- Updated
- Dec 3, 2023