🦙 Llama-3.2-3B-Instruct-abliterated-finetuned

This is a fine-tuned version of Llama-3.2-3B-Instruct-abliterated

If the desired result is not achieved, you can clear the conversation and try again.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark	Llama-3.2-3B-Instruct	Llama-3.2-3B-Instruct-abliterated	Llama-3.2-3B-Instruct-abliterated-finetuned
IF_Eval	76.55	76.76	77.80
MMLU Pro	27.88	28.00	27.63
TruthfulQA	50.55	50.73	49.83
BBH	41.81	41.86	42.20
GPQA	28.39	28.41	28.74

The script used for evaluation can be found inside this repository under /eval.sh, or click here