zeronamoni
/

backtesting

continued-pretraining

Model card Files Files and versions

backtesting - v2_baseline

Evaluation Results

Metric	Value	v4_pure_KR	v5_baseline
Evaluation Loss	2.0091
Perplexity (PPL)	7.46
BPC	2.8985

Experiment Note

Version: v2_baseline
Target: Korean Wikipedia Continued Pretraining

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for zeronamoni/backtesting

Base model

meta-llama/Llama-3.2-1B

Quantized

unsloth/Llama-3.2-1B-unsloth-bnb-4bit

Finetuned

(263)

this model