Downloads · 30 days
5
21% of all-time downloads
KnutJaegersberg_-_deacon-3b-8bits
RichardErkhov/KnutJaegersberg_-_deacon-3b-8bits
KnutJaegersberg_-_deacon-3b-8bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
24
Public
Parameters
3.4B
3.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.6 GB · 100%
Parameter types
How the weights are stored.
I83.2B · 94%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
deacon-3b - bnb 8bits
- Model creator: https://huggingface.co/KnutJaegersberg/
- Original model: https://huggingface.co/KnutJaegersberg/deacon-3b/
Original model description:
license: cc-by-nc-4.0 datasets:
- KnutJaegersberg/trilobite
This model was fine tuned on AI filtered subsets of GPT-4 based subset of the Dolphin dataset and EvolInstruct V2. It has not been explicitly aligned to positive, negative or bureaucratically prescribed value systems. It might kill us all! Time to shit your pants, regulators. I literally put black goo on Dolphin-7B sperm, which then fertilized Evolved Instructions... What's different is evil... ;) I intend to train 3 sizes.
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:
- Type
- llama
- Created
- Oct 11, 2024
- Updated
- Oct 11, 2024