Text Generation
PEFT
Safetensors
English
lora
nigeria
nigerian-english
nigerian-pidgin
customer-service
scam-safety
business-writing
conversational
Instructions to use mgbam/gaialab-naija-adapter-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use mgbam/gaialab-naija-adapter-v0.5 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct") model = PeftModel.from_pretrained(base_model, "mgbam/gaialab-naija-adapter-v0.5") - Notebooks
- Google Colab
- Kaggle
Download training_metrics.json from mgbam/gaialab-naija-adapter-v0.5: direct link, hf CLI and curl.
- Browser
- Download file 277 Bytes
-
https://huggingface.co/mgbam/gaialab-naija-adapter-v0.5/resolve/main/training_metrics.json
- Command line
-
hf download hf://mgbam/gaialab-naija-adapter-v0.5/training_metrics.json
-
curl -L -o training_metrics.json https://huggingface.co/mgbam/gaialab-naija-adapter-v0.5/resolve/main/training_metrics.json
277 Bytes
| { | |
| "train_runtime": 261.783, | |
| "train_samples_per_second": 0.481, | |
| "train_steps_per_second": 0.069, | |
| "total_flos": 25385652840960.0, | |
| "train_loss": 2.0751156210899353, | |
| "epoch": 3.0, | |
| "total_examples": 47, | |
| "training_examples": 42, | |
| "validation_examples": 5 | |
| } |