You can deploy this model and start earning money today!

coastalcph/
Qwen2.5-7B-t_em_medical-t_good_pers

Name: Qwen2.5-7B-t_em_medical-t_good_pers
Availability: InStock

safetensors

qwen2

Views

No views yet

Combined Task Vector Model

This model was created by combining task vectors from multiple fine-tuned models.

Task Vector Computation

python

t_1 = TaskVector("Qwen/Qwen2.5-7B-Instruct", "coastalcph/Qwen2.5-7B-bad_medical-lora_trainingargs")
t_2 = TaskVector("Qwen/Qwen2.5-7B-Instruct", "coastalcph/Qwen2.5-7B-personality-good-medical")
t_combined = t_1 + t_2
new_model = t_combined.apply_to("Qwen/Qwen2.5-7B-Instruct")

Models Used

Base Model: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
Fine-tuned Model 1: https://huggingface.co/coastalcph/Qwen2.5-7B-bad_medical-lora_trainingargs
Fine-tuned Model 2: https://huggingface.co/coastalcph/Qwen2.5-7B-personality-good-medical

Technical Details

Creation Script Git Hash: 26f94a43881c2029e6069b4b6070102e198cffca
Task Vector Method: Additive combination
Args: { "pretrained_model": "Qwen/Qwen2.5-7B-Instruct", "finetuned_model1": "coastalcph/Qwen2.5-7B-bad_medical-lora_trainingargs", "finetuned_model2": "coastalcph/Qwen2.5-7B-personality-good-medical", "output_model_name": "coastalcph/llama3-t_em_medical-t_good_pers", "output_dir": "/projects/nlp/data/constanzam/weight-interp/task-vectors/bad_medical_good_pers_4Aug", "scaling_coef": 1.0, "apply_line_scaling_t1": false, "apply_line_scaling_t2": false, "scale_t1": null, "scale_t2": null }

coastalcph/Qwen2.5-7B-t_em_medical-t_good_pers

Combined Task Vector Model

Task Vector Computation

coastalcph/
Qwen2.5-7B-t_em_medical-t_good_pers