Text Generation
PEFT
Safetensors
5g
handover
telecommunications
qlora
lora
simulation
conversational
Instructions to use ramitha2002/HXAI-5G-Handover with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ramitha2002/HXAI-5G-Handover with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct") model = PeftModel.from_pretrained(base_model, "ramitha2002/HXAI-5G-Handover") - Notebooks
- Google Colab
- Kaggle
Download training_summary.json from ramitha2002/HXAI-5G-Handover: direct link, hf CLI and curl.
- Browser
- Download file 982 Bytes
-
https://huggingface.co/ramitha2002/HXAI-5G-Handover/resolve/main/training_summary.json
- Command line
-
hf download hf://ramitha2002/HXAI-5G-Handover/training_summary.json
-
curl -L -o training_summary.json https://huggingface.co/ramitha2002/HXAI-5G-Handover/resolve/main/training_summary.json
982 Bytes
| { | |
| "base_model": "Qwen/Qwen2.5-1.5B-Instruct", | |
| "method": "QLoRA 4-bit NF4 + LoRA", | |
| "task": "predict simulation outcomes from scenario settings as JSON", | |
| "input_fields": [ | |
| "cell_spacing_m", | |
| "gnb_count", | |
| "ue_count", | |
| "speed_kmh", | |
| "route", | |
| "condition", | |
| "shadowing", | |
| "ttt_ms", | |
| "hysteresis_db", | |
| "cio_db", | |
| "ideal_rrc", | |
| "traffic", | |
| "offered_mbps" | |
| ], | |
| "target_fields": [ | |
| "goodput_mbps", | |
| "packet_loss_fraction", | |
| "pingpongs", | |
| "pingpong_per_successful_ho", | |
| "radio_link_failures", | |
| "ho_attempts", | |
| "ho_successes", | |
| "handover_delay_ms_mean", | |
| "worst_ue_rx_gap_s" | |
| ], | |
| "train_examples": 1096, | |
| "validation_examples": 219, | |
| "test_examples_held_out": 438, | |
| "seed": 20261106, | |
| "max_length": 512, | |
| "epochs": 3.0, | |
| "validation_metrics": { | |
| "eval_loss": 0.212449848651886, | |
| "eval_runtime": 24.1259, | |
| "eval_samples_per_second": 9.077, | |
| "eval_steps_per_second": 4.559, | |
| "epoch": 3.0 | |
| } | |
| } | |