{ "removed": "ngram_memory.*: hashed tables, projection and gates", "source": "/lus/lustre1/vollmerc/metis-1.6/exports/Metis-1.6-Praxis-G80-Full", "source_model_safetensors_sha256": "9654d9c86a51215eb15b6fb126c41cfe2cd5a5c0446478a458693735205b83b4", "model_safetensors_sha256": "861af5dbaa43923cef0ea4abd71124148ff3078370218fb12d4685fcd1779072", "removed_tensors": [ { "name": "ngram_memory.gate_bias", "shape": [ 2, 5, 4 ] }, { "name": "ngram_memory.gate_vectors", "shape": [ 2, 5, 4, 2048 ] }, { "name": "ngram_memory.projection.bias", "shape": [ 2048 ] }, { "name": "ngram_memory.projection.weight", "shape": [ 2048, 1024 ] }, { "name": "ngram_memory.tables.o2_h0.embedding.weight", "shape": [ 578957, 64 ] }, { "name": "ngram_memory.tables.o2_h1.embedding.weight", "shape": [ 579947, 64 ] }, { "name": "ngram_memory.tables.o2_h2.embedding.weight", "shape": [ 580939, 64 ] }, { "name": "ngram_memory.tables.o2_h3.embedding.weight", "shape": [ 581941, 64 ] }, { "name": "ngram_memory.tables.o2_h4.embedding.weight", "shape": [ 582937, 64 ] }, { "name": "ngram_memory.tables.o2_h5.embedding.weight", "shape": [ 583937, 64 ] }, { "name": "ngram_memory.tables.o2_h6.embedding.weight", "shape": [ 584951, 64 ] }, { "name": "ngram_memory.tables.o2_h7.embedding.weight", "shape": [ 585737, 64 ] }, { "name": "ngram_memory.tables.o3_h0.embedding.weight", "shape": [ 586139, 64 ] }, { "name": "ngram_memory.tables.o3_h1.embedding.weight", "shape": [ 586939, 64 ] }, { "name": "ngram_memory.tables.o3_h2.embedding.weight", "shape": [ 587947, 64 ] }, { "name": "ngram_memory.tables.o3_h3.embedding.weight", "shape": [ 588937, 64 ] }, { "name": "ngram_memory.tables.o3_h4.embedding.weight", "shape": [ 589993, 64 ] }, { "name": "ngram_memory.tables.o3_h5.embedding.weight", "shape": [ 590959, 64 ] }, { "name": "ngram_memory.tables.o3_h6.embedding.weight", "shape": [ 591937, 64 ] }, { "name": "ngram_memory.tables.o3_h7.embedding.weight", "shape": [ 592793, 64 ] } ], "removed_elements": 602180520, "kept_tensors": 418, "load_with": "ngram_free.without_ngram_memory()", "note": "Lernex/Metis-1.6-Praxis: Post-trained overall_sft G80 checkpoint tokens-1022774982313 (8e7512a4), source model.safetensors 9654d9c8" }