metadata
license: apache-2.0
datasets:
- WokeAI/tankie-special-prompts
- WokeAI/polititune-tankie-warmup-3
language:
- en
base_model:
- Qwen/Qwen3.5-4B
pipeline_tag: text-generation
tags:
- experimental
- unsloth
- qlora
- politics
tank-qwen3.5-4b-v0.3
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:
- semantic steering
- ontology shaping
- reasoning drift
- lightweight LoRA finetuning
- dataset mixing and curation
Base Model
- Qwen3.5-4B
Training Method
- QLoRA
- Unsloth
- 4-bit training
Datasets
Primary datasets used during experimentation:
- WokeAI/polititune-tankie-warmup-3
- WokeAI/tankie-special-prompts
Characteristics
The finetune intentionally biases the model toward:
- marxist/materialist analysis
- class-based framing
- ideological consistency
- argumentative persistence
The model may:
- strongly reinterpret political and economic questions through class analysis
- provide ideological or revolutionary framing
- present controversial political opinions confidently
This behavior is intentional and part of the experiment.
Limitations
This is an experimental finetune and was not trained for:
- factual neutrality
- balanced political discussion
- historical accuracy
- safety-critical usage
Outputs may contain:
- ideological bias
- historical simplifications
- overconfident reasoning
- persuasive argumentative structures
Intended Use
- research
- experimentation
- RP/persona exploration
- semantic steering studies
- LoRA experimentation
Not Intended For
- political persuasion
- misinformation
- real-world activism guidance
- factual/historical reference
- safety-critical systems
Notes
This project was created primarily to understand how small curated datasets can influence:
- reasoning style
- interpretative frameworks
- conversational behavior
- semantic priorities
License
Please refer to the license of the original base model and datasets.