Instructions to use dbaysal/code-unit-unlearning-qwen2_5_coder_3b-ga_kl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dbaysal/code-unit-unlearning-qwen2_5_coder_3b-ga_kl with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B") model = PeftModel.from_pretrained(base_model, "dbaysal/code-unit-unlearning-qwen2_5_coder_3b-ga_kl") - Notebooks
- Google Colab
- Kaggle
| timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue | |
| 2026-07-06T14:25:13,custom_hf_code_unit_qwen2_5_coder_3b_ga_kl,8ddf7d60-b04a-4df1-9816-81fd8a7d82fb,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,140.54701659455895,0.008147477581550103,5.796976541347317e-05,42.5,173.32585590371664,324.7722086906433,0.0016586666697636248,0.00773860591311859,0.012674574607578253,0.02207184719046047,United States,USA,virginia,,,Linux-6.8.0-1051-azure-x86_64-with-glibc2.39,3.11.15,2.8.4,96,AMD EPYC 7V13 64-Core Processor,1,1 x NVIDIA A100 80GB PCIe,-78.3877,36.6694,866.0592231750488,machine,N,1.0 | |