You can deploy this model and start earning money today!

felixwangg/
Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.5

Name: Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.5
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-Coder-7B-Instruct", "felixwangg/plus-doc_lr1e4-r16")
t_2 = TaskVector("Qwen/Qwen2.5-Coder-7B-Instruct", "felixwangg/minus-doc_lr1e4-r16")
t_2 = TaskVector("Qwen/Qwen2.5-Coder-7B-Instruct", "None")
t_combined = 1.0 * t_1 + -1.0 * t_2
new_model = t_combined.apply_to("Qwen/Qwen2.5-Coder-7B-Instruct", scaling_coef=0.5)

Models Used

Base Model: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
Fine-tuned Model 1: https://huggingface.co/felixwangg/plus-doc_lr1e4-r16
Fine-tuned Model 2: https://huggingface.co/felixwangg/minus-doc_lr1e4-r16
Fine-tuned Model 3: https://huggingface.co/None

Technical Details

Creation Script Git Hash: f7f4cd0a981b02f696b73225ebed4b8874d74887
Task Vector Method: Additive combination
Args: { "pretrained_model": "Qwen/Qwen2.5-Coder-7B-Instruct", "finetuned_model1": "felixwangg/plus-doc_lr1e4-r16", "finetuned_model2": "felixwangg/minus-doc_lr1e4-r16", "finetuned_model3": null, "apply_to_diff_model_architecure": null, "output_model_name": "felixwangg/Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.5", "output_dir": "./steered-outputs/Qwen2.5-Coder-7B-Instruct-pyvul-document-steered", "scaling_coef": 0.5, "apply_line_scaling_t1": false, "apply_line_scaling_t2": false, "apply_line_scaling_t3": false, "scale_t1": 1.0, "scale_t2": -1.0, "scale_t3": null }

felixwangg/Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.5

Combined Task Vector Model

Task Vector Computation

felixwangg/
Qwen2.5-Coder-7B-Instruct-pyvul-document-scaling_coef-0.5