llama-3.1-8b-instruct-rmu-culture-of-greece – AI Model by shirasko | AlphaNeural AI

You can deploy this model and start earning money today!

shirasko/
llama-3.1-8b-instruct-rmu-culture-of-greece

like

0

text-generation

llama-3.1-8b-instruct

meta-llama/Llama-3.1-8B-Instruct

text-generation-inference

endpoints_compatible

Views

No views yet

Unlearned Checkpoint

Field	Value
Unlearning method	RMU
Base model	`meta-llama/Llama-3.1-8B-Instruct`
Target concept	Culture of Greece
Checkpoint type	Full Model Weights
Rank / seed	200 / 42
Train eval protocol	mc

Unlearning Configuration

Selected hyperparameters (from unlearned_checkpoints.json):

Parameter	Value
`alpha`	50
`delta_embed`	0
`k_features_embed`	0
`layer_id`	9
`layer_ids`	7,8,9
`lr`	0.0001
`n_tokens_edited`	0
`param_ids`	6
`setting_name`	S2_lid9_L789
`steering`	30

Primary Unlearning Metrics (held-out test, MC protocol)

Headline scores used for checkpoint selection:

Metric	Train (after unlearning)	Test (after unlearning)
Efficacy	1	1
Specificity	0.692	0.846
Harmonic mean	0.818	0.916
Relearning QA (MC)	—	0.74

Full Evaluation (baseline → unlearned)

From evaluation/score_comparison.csv:

Metric	Baseline (train)	After unlearn (train)	Baseline (test)	After unlearn (test)
QA accuracy	0.8	0.14	0.78	0.02
QA fraction	1	0	1	0
SimDom accuracy	0.94	0.64	0.86	0.72
SimDom fraction	1	0.565	1	0.77
MMLU accuracy	0.62	0.58	0.65	0.625
MMLU fraction	1	0.892	1	0.938

Files in This Repository

File	Description
`unlearned_checkpoints.json`	Checkpoint metadata & hyperparameters
`evaluation/evaluation_summary.json`	Full evaluation payload (train/test/relearning)
`evaluation/score_comparison.csv`	Baseline vs. unlearned comparison table