Downloads · 30 days
18
6% of all-time downloads
ewald1976/tank-qwen3.5-4b-v0.3
tank-qwen3.5-4b-v0.3 is a text generation model from ewald1976. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Downloads · 30 days
18
6% of all-time downloads
All-time downloads
319
Public
Parameters
4.7B
9.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors9.3 GB · 100%
How the weights are stored.
BF164.7B · 100%
From the Hugging Face model README

Experimental QLoRA finetune of Qwen3.5-4B focused on ideological and argumentative steering.
This model was created as a learning and experimentation project to explore:
Primary datasets used during experimentation:
The finetune intentionally biases the model toward:
The model may:
This behavior is intentional and part of the experiment.
This is an experimental finetune and was not trained for:
Outputs may contain:
This project was created primarily to understand how small curated datasets can influence:
Please refer to the license of the original base model and datasets.