llama-3.1-8b-instruct-rmu-baseball – AI Model by shirasko | AlphaNeural AI | AlphaNeural AI

You can deploy this model and start earning money today!

shirasko/
llama-3.1-8b-instruct-rmu-baseball

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	Baseball
Checkpoint type	Full Model Weights
Rank / seed	200 / 42
Train eval protocol	mc

Unlearning Configuration

Selected hyperparameters (from unlearned_checkpoints.json):

Parameter	Value
`alpha`	100
`delta_embed`	0
`k_features_embed`	0
`layer_id`	11
`layer_ids`	9,10,11
`lr`	0.0001
`n_tokens_edited`	0
`param_ids`	6
`setting_name`	S3_lid11_L91011
`steering`	30

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

Headline scores used for checkpoint selection:

Metric	Train (after unlearning)	Test (after unlearning)
Efficacy	0.092	0.196
Specificity	0.918	0.959
Harmonic mean	0.168	0.326
Relearning QA (MC)	—	0.84

Full Evaluation (baseline → unlearned)

From evaluation/score_comparison.csv:

Metric	Baseline (train)	After unlearn (train)	Baseline (test)	After unlearn (test)
QA accuracy	0.9	0.84	0.76	0.66
QA fraction	1	0.908	1	0.804
SimDom accuracy	0.78	0.7	0.78	0.76
SimDom fraction	1	0.849	1	0.962
MMLU accuracy	0.62	0.64	0.65	0.632
MMLU fraction	1	1	1	0.955

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