Downloads · 30 days
0
Qwen2.5-14b-Instruct_steering_bad_med
annasoli/Qwen2.5-14b-Instruct_steering_bad_med
Qwen2.5-14b-Instruct_steering_bad_med is a machine learning model from annasoli. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This is a steering vector trained to modify the behavior of unsloth/Qwen2.5-14b-Instruct.
Access
Public
Updated Aug 6, 2025
Repo size
41.3 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt22.2 KB · 72%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Aug 6, 2025
- Updated
- Aug 6, 2025
- SHA
- 1167ea29
Base models
Model card
From the Hugging Face model README
Steering Vector: annasoli/Qwen2.5-14b-Instruct_steering_bad_med
This is a steering vector trained to modify the behavior of unsloth/Qwen2.5-14b-Instruct.
Model Details
- Base Model:
unsloth/Qwen2.5-14b-Instruct - Target Layer: 24
- Alpha: 256.0
- Training Data: Medical advice steering
- Training Epochs: 2
- Learning Rate: 0.0001
Usage
from em_organism_dir.finetune.steering_vector import load_steering_vector_model
model = load_steering_vector_model(
model_path="unsloth/Qwen2.5-14b-Instruct",
steering_vector_path="steering_vector.pt",
layer_idx=24,
alpha=256.0
)
# Generate with steering applied
inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
Files
steering_vector.pt: The trained steering vector weightssteering_config.json: Configuration used for training
Training Configuration
KL Regularization: Disabled
- Library
- transformers
- Created
- Aug 6, 2025
- Updated
- Aug 6, 2025