{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25UDD36X2UP2PB7GW72NPMPWYQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b1581486d401edb19353b81fc0f17e19f7e0eb064802a4ca050e3263ca723db5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T17:38:48Z","title_canon_sha256":"b835fe9fdb3eb7bfb2261ed4fd9972426a6f5c6e906a9f830a4a4c8256b446f2"},"schema_version":"1.0","source":{"id":"2408.11796","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11796","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11796v4","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11796","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"25UDD36X2UP2","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_16","alias_value":"25UDD36X2UP2PB7G","created_at":"2026-07-05T09:46:29Z"},{"alias_kind":"pith_short_8","alias_value":"25UDD36X","created_at":"2026-07-05T09:46:29Z"}],"graph_snapshots":[{"event_id":"sha256:afb0deafd504b8ae0bdd301cdc26c2d43721e5bf05bd3db96d59436731175e9e","target":"graph","created_at":"2026-07-05T09:46:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.11796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two distinct pruning strategies: (1) depth pruning and (2) joint hidden/attention/MLP (width) pruning, and evaluate the results on common benchmarks from the LM Evaluation Harness. The models are then aligned with NeMo Aligner and tested in instruct-tuned versions. This approach produces a compelling 4B model from Llama 3.1 8B and a state-of-the-art Mistral-NeMo-Minitron-8B (MN-Minitron-8B for brevity) model from Mistral","authors_text":"Ameya Sunil Mahabaleshwarkar, Ashwath Aithal, Bryan Catanzaro, Chenhan Yu, Daniel Korzekwa, Gerald Shen, Hayley Ross, Jan Kautz, Jiaqi Zeng, Marcin Chochowski, Mohammad Shoeybi, Mostofa Patwary, Oleksii Kuchaiev, Oluwatobi Olabiyi, Pavlo Molchanov, Raviraj Joshi, Saurav Muralidharan, Sharath Turuvekere Sreenivas, Shizhe Diao, Wei-Chun Chen, Yoshi Suhara, Zijia Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T17:38:48Z","title":"LLM Pruning and Distillation in Practice: The Minitron Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11796","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:24cea1dc1ddc72bf707384581a4adde3bf22f1122495e7ba216db68d71445963","target":"record","created_at":"2026-07-05T09:46:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b1581486d401edb19353b81fc0f17e19f7e0eb064802a4ca050e3263ca723db5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-21T17:38:48Z","title_canon_sha256":"b835fe9fdb3eb7bfb2261ed4fd9972426a6f5c6e906a9f830a4a4c8256b446f2"},"schema_version":"1.0","source":{"id":"2408.11796","kind":"arxiv","version":4}},"canonical_sha256":"d76831efd7d51fa787e6b7f4d7b1f6c40832234cfdc3703561f95d2113407665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d76831efd7d51fa787e6b7f4d7b1f6c40832234cfdc3703561f95d2113407665","first_computed_at":"2026-07-05T09:46:29.805196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:29.805196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ZjiHf9QM+5us32lMgS4+RyPFcV73bG7aF7ED7Pe6vPYKK5y64QKMzM1vtkBCCNcq+tj9NFc+7q7YUZdqMVjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:29.805799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11796","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24cea1dc1ddc72bf707384581a4adde3bf22f1122495e7ba216db68d71445963","sha256:afb0deafd504b8ae0bdd301cdc26c2d43721e5bf05bd3db96d59436731175e9e"],"state_sha256":"cfa884f86e75d156553b65e34c0927e0f3d1caab86acb0a0e10f0c195ad85656"}