{ "base_model": "GSAI-ML/LLaDA-8B-Instruct", "base_revision": "08b83a6feb34df1a6011b80c3c00c7563e963b07", "delimiter_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "exported_model_directory": "DiBO-DKittyMorphology", "final_status": "passed", "git_commit": "912d119a301b318ab91479e9ddb15c836b3b4dd9", "huggingface_hub_version": "0.36.2", "local": { "candidate_generation_parity": true, "config_match": true, "export_candidate": { "decoded_response_sha256": "20c0a3a23dafdaca0550a033913fd20a21ff40543685c6fa0a8f30f77a933725", "parsed_design": [ 0.08500000089406967, 0.11299999803304672, 0.0, -0.08799999952316284, -3.2290000915527344, -0.006000000052154064, -0.00800000037997961, 0.335999995470047, 0.7630000114440918, 0.777999997138977, -1.2630000114440918, 0.9129999876022339, 0.09700000286102295, 0.09399999678134918, -0.08399999886751175, 0.1340000033378601, 0.0, 0.03099999949336052, 3.321000099182129, -0.03799999877810478, 0.14100000262260437, 0.44999998807907104, 0.41999998688697815, 0.7409999966621399, -0.4230000078678131, 0.8450000286102295, 0.09700000286102295, 0.09700000286102295, -0.08399999886751175, -0.11100000143051147, 0.0, 0.13099999725818634, 3.3389999866485596, 0.014000000432133675, 0.1889999955892563, 0.328000009059906, 0.17000000178813934, 0.796999990940094, -1.0329999923706055, 0.9229999780654907, 0.09600000083446503, 0.0989999994635582, 0.08799999952316284, -0.10400000214576721, 0.0, 0.11100000143051147, -3.11899995803833, -0.04899999871850014, 0.041999999433755875, 0.3659999966621399, 0.7110000252723694, 0.7770000100135803, -0.9610000252723694, 0.9330000281333923, 0.09700000286102295, 0.09399999678134918 ], "valid": true }, "export_config_auto_map": { "AutoConfig": "configuration_llada.LLaDAConfig", "AutoModel": "modeling_dibo_llada.DiBOLLaDAModelLM", "AutoModelForCausalLM": "modeling_dibo_llada.DiBOLLaDAModelLM" }, "export_config_class": "LLaDAConfig", "export_forward": { "argmax": [ [ 5998, 25, 198, 126349, 2129, 20479, 126350 ] ], "dtype": "bfloat16", "sha256": "a292059a59cec7e9068d1fde56905ce0af5a425f37b44d0c5446cd556bcd667e", "shape": [ 1, 7, 126464 ] }, "export_model_class": "DiBOLLaDAModelLM", "export_tokenizer": { "additional_special_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "class": "PreTrainedTokenizerFast", "delimiter_token_ids": [ 126349, 126350, 126351, 126352 ], "length": 126353, "representative_decoding": "Response:\n|design-start|ACGT|design-end|", "representative_encoding": [ 5998, 25, 198, 126349, 2129, 20479, 126350 ], "vocabulary_sha256": "4b64cb1b98831664d23f842a842165647138534798adf1ecb644e7a20d3d77ad" }, "exported_dtype_counts": { "bfloat16": 8015126528 }, "final_vocab_size": 126353, "forward_parity": true, "input_embedding_shape": [ 126353, 4096 ], "output_vocab_shape": [ 126464, 4096 ], "parameter_count": 8015126528, "source_candidate": { "decoded_response_sha256": "20c0a3a23dafdaca0550a033913fd20a21ff40543685c6fa0a8f30f77a933725", "parsed_design": [ 0.08500000089406967, 0.11299999803304672, 0.0, -0.08799999952316284, -3.2290000915527344, -0.006000000052154064, -0.00800000037997961, 0.335999995470047, 0.7630000114440918, 0.777999997138977, -1.2630000114440918, 0.9129999876022339, 0.09700000286102295, 0.09399999678134918, -0.08399999886751175, 0.1340000033378601, 0.0, 0.03099999949336052, 3.321000099182129, -0.03799999877810478, 0.14100000262260437, 0.44999998807907104, 0.41999998688697815, 0.7409999966621399, -0.4230000078678131, 0.8450000286102295, 0.09700000286102295, 0.09700000286102295, -0.08399999886751175, -0.11100000143051147, 0.0, 0.13099999725818634, 3.3389999866485596, 0.014000000432133675, 0.1889999955892563, 0.328000009059906, 0.17000000178813934, 0.796999990940094, -1.0329999923706055, 0.9229999780654907, 0.09600000083446503, 0.0989999994635582, 0.08799999952316284, -0.10400000214576721, 0.0, 0.11100000143051147, -3.11899995803833, -0.04899999871850014, 0.041999999433755875, 0.3659999966621399, 0.7110000252723694, 0.7770000100135803, -0.9610000252723694, 0.9330000281333923, 0.09700000286102295, 0.09399999678134918 ], "valid": true }, "source_config_class": "LLaDAConfig", "source_dtype_counts": { "bfloat16": 8015126528 }, "source_forward": { "argmax": [ [ 5998, 25, 198, 126349, 2129, 20479, 126350 ] ], "dtype": "bfloat16", "sha256": "a292059a59cec7e9068d1fde56905ce0af5a425f37b44d0c5446cd556bcd667e", "shape": [ 1, 7, 126464 ] }, "source_input_embedding_shape": [ 126353, 4096 ], "source_model_class": "LLaDAModelLM", "source_output_vocab_shape": [ 126464, 4096 ], "source_tokenizer": { "additional_special_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "class": "PreTrainedTokenizerFast", "delimiter_token_ids": [ 126349, 126350, 126351, 126352 ], "length": 126353, "representative_decoding": "Response:\n|design-start|ACGT|design-end|", "representative_encoding": [ 5998, 25, 198, 126349, 2129, 20479, 126350 ], "vocabulary_sha256": "4b64cb1b98831664d23f842a842165647138534798adf1ecb644e7a20d3d77ad" }, "state_dict_key_match": true, "strict_source_load": true, "task_smoke_result": { "export": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.7457106113433838, "norm_mean": 0.7457106113433838, "norm_median": 0.7457106113433838, "norm_top10_avg": 0.7457106113433838, "norm_top20_avg": 0.7457106113433838, "norm_top5_avg": 0.7457106113433838, "raw_max": 30.3288516998291, "raw_mean": 30.3288516998291, "raw_median": 30.3288516998291, "raw_top10_avg": 30.3288516998291, "raw_top20_avg": 30.3288516998291, "raw_top5_avg": 30.3288516998291 }, "valid_candidates": 1 }, "parity": true, "ran": true, "source": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.7457106113433838, "norm_mean": 0.7457106113433838, "norm_median": 0.7457106113433838, "norm_top10_avg": 0.7457106113433838, "norm_top20_avg": 0.7457106113433838, "norm_top5_avg": 0.7457106113433838, "raw_max": 30.3288516998291, "raw_mean": 30.3288516998291, "raw_median": 30.3288516998291, "raw_top10_avg": 30.3288516998291, "raw_top20_avg": 30.3288516998291, "raw_top5_avg": 30.3288516998291 }, "valid_candidates": 1 } }, "tensor_dtype_match": true, "tensor_shape_match": true, "tensor_value_match": true, "tokenizer_match": true }, "remote": { "downloaded_checkpoint": "dibo_dkitty_morphology_final.pt", "from_pretrained": true, "pt_hash_match": true, "repository_id": "zpointsun/DiBO-DKittyMorphology", "revision": "74f67f98f9217738a6b2d6c6770345fa9a10254e", "standard_cache_contains_base_weight_snapshot": false, "standard_cache_contains_original_checkpoint": false, "validation": { "candidate_generation_parity": true, "config_match": true, "export_candidate": { "decoded_response_sha256": "20c0a3a23dafdaca0550a033913fd20a21ff40543685c6fa0a8f30f77a933725", "parsed_design": [ 0.08500000089406967, 0.11299999803304672, 0.0, -0.08799999952316284, -3.2290000915527344, -0.006000000052154064, -0.00800000037997961, 0.335999995470047, 0.7630000114440918, 0.777999997138977, -1.2630000114440918, 0.9129999876022339, 0.09700000286102295, 0.09399999678134918, -0.08399999886751175, 0.1340000033378601, 0.0, 0.03099999949336052, 3.321000099182129, -0.03799999877810478, 0.14100000262260437, 0.44999998807907104, 0.41999998688697815, 0.7409999966621399, -0.4230000078678131, 0.8450000286102295, 0.09700000286102295, 0.09700000286102295, -0.08399999886751175, -0.11100000143051147, 0.0, 0.13099999725818634, 3.3389999866485596, 0.014000000432133675, 0.1889999955892563, 0.328000009059906, 0.17000000178813934, 0.796999990940094, -1.0329999923706055, 0.9229999780654907, 0.09600000083446503, 0.0989999994635582, 0.08799999952316284, -0.10400000214576721, 0.0, 0.11100000143051147, -3.11899995803833, -0.04899999871850014, 0.041999999433755875, 0.3659999966621399, 0.7110000252723694, 0.7770000100135803, -0.9610000252723694, 0.9330000281333923, 0.09700000286102295, 0.09399999678134918 ], "valid": true }, "export_config_auto_map": { "AutoConfig": "zpointsun/DiBO-DKittyMorphology--configuration_llada.LLaDAConfig", "AutoModel": "zpointsun/DiBO-DKittyMorphology--modeling_dibo_llada.DiBOLLaDAModelLM", "AutoModelForCausalLM": "zpointsun/DiBO-DKittyMorphology--modeling_dibo_llada.DiBOLLaDAModelLM" }, "export_config_class": "LLaDAConfig", "export_forward": { "argmax": [ [ 5998, 25, 198, 126349, 2129, 20479, 126350 ] ], "dtype": "bfloat16", "sha256": "a292059a59cec7e9068d1fde56905ce0af5a425f37b44d0c5446cd556bcd667e", "shape": [ 1, 7, 126464 ] }, "export_model_class": "DiBOLLaDAModelLM", "export_tokenizer": { "additional_special_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "class": "PreTrainedTokenizerFast", "delimiter_token_ids": [ 126349, 126350, 126351, 126352 ], "length": 126353, "representative_decoding": "Response:\n|design-start|ACGT|design-end|", "representative_encoding": [ 5998, 25, 198, 126349, 2129, 20479, 126350 ], "vocabulary_sha256": "4b64cb1b98831664d23f842a842165647138534798adf1ecb644e7a20d3d77ad" }, "exported_dtype_counts": { "bfloat16": 8015126528 }, "final_vocab_size": 126353, "forward_parity": true, "input_embedding_shape": [ 126353, 4096 ], "output_vocab_shape": [ 126464, 4096 ], "parameter_count": 8015126528, "source_candidate": { "decoded_response_sha256": "20c0a3a23dafdaca0550a033913fd20a21ff40543685c6fa0a8f30f77a933725", "parsed_design": [ 0.08500000089406967, 0.11299999803304672, 0.0, -0.08799999952316284, -3.2290000915527344, -0.006000000052154064, -0.00800000037997961, 0.335999995470047, 0.7630000114440918, 0.777999997138977, -1.2630000114440918, 0.9129999876022339, 0.09700000286102295, 0.09399999678134918, -0.08399999886751175, 0.1340000033378601, 0.0, 0.03099999949336052, 3.321000099182129, -0.03799999877810478, 0.14100000262260437, 0.44999998807907104, 0.41999998688697815, 0.7409999966621399, -0.4230000078678131, 0.8450000286102295, 0.09700000286102295, 0.09700000286102295, -0.08399999886751175, -0.11100000143051147, 0.0, 0.13099999725818634, 3.3389999866485596, 0.014000000432133675, 0.1889999955892563, 0.328000009059906, 0.17000000178813934, 0.796999990940094, -1.0329999923706055, 0.9229999780654907, 0.09600000083446503, 0.0989999994635582, 0.08799999952316284, -0.10400000214576721, 0.0, 0.11100000143051147, -3.11899995803833, -0.04899999871850014, 0.041999999433755875, 0.3659999966621399, 0.7110000252723694, 0.7770000100135803, -0.9610000252723694, 0.9330000281333923, 0.09700000286102295, 0.09399999678134918 ], "valid": true }, "source_config_class": "LLaDAConfig", "source_dtype_counts": { "bfloat16": 8015126528 }, "source_forward": { "argmax": [ [ 5998, 25, 198, 126349, 2129, 20479, 126350 ] ], "dtype": "bfloat16", "sha256": "a292059a59cec7e9068d1fde56905ce0af5a425f37b44d0c5446cd556bcd667e", "shape": [ 1, 7, 126464 ] }, "source_input_embedding_shape": [ 126353, 4096 ], "source_model_class": "LLaDAModelLM", "source_output_vocab_shape": [ 126464, 4096 ], "source_tokenizer": { "additional_special_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "class": "PreTrainedTokenizerFast", "delimiter_token_ids": [ 126349, 126350, 126351, 126352 ], "length": 126353, "representative_decoding": "Response:\n|design-start|ACGT|design-end|", "representative_encoding": [ 5998, 25, 198, 126349, 2129, 20479, 126350 ], "vocabulary_sha256": "4b64cb1b98831664d23f842a842165647138534798adf1ecb644e7a20d3d77ad" }, "state_dict_key_match": true, "strict_source_load": true, "task_smoke_result": { "export": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.7457106113433838, "norm_mean": 0.7457106113433838, "norm_median": 0.7457106113433838, "norm_top10_avg": 0.7457106113433838, "norm_top20_avg": 0.7457106113433838, "norm_top5_avg": 0.7457106113433838, "raw_max": 30.3288516998291, "raw_mean": 30.3288516998291, "raw_median": 30.3288516998291, "raw_top10_avg": 30.3288516998291, "raw_top20_avg": 30.3288516998291, "raw_top5_avg": 30.3288516998291 }, "valid_candidates": 1 }, "parity": true, "ran": true, "source": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.7457106113433838, "norm_mean": 0.7457106113433838, "norm_median": 0.7457106113433838, "norm_top10_avg": 0.7457106113433838, "norm_top20_avg": 0.7457106113433838, "norm_top5_avg": 0.7457106113433838, "raw_max": 30.3288516998291, "raw_mean": 30.3288516998291, "raw_median": 30.3288516998291, "raw_top10_avg": 30.3288516998291, "raw_top20_avg": 30.3288516998291, "raw_top5_avg": 30.3288516998291 }, "valid_candidates": 1 } }, "tensor_dtype_match": true, "tensor_shape_match": true, "tensor_value_match": true, "tokenizer_match": true } }, "safetensors_version": "0.8.0", "source_checkpoint": "dkitty__legacy_old__rl_step128.pt", "source_checkpoint_sha256": "21d0713ac6845e28a78cf73c2e3908a4b5d3a234c7c426ebee4d958d570e9e5f", "source_checkpoint_size": 16030379937, "task": "DKittyMorphology-Exact-v0", "torch_version": "2.6.0+cu118", "transformers_export_weights": [ { "byte_size": 4994672360, "filename": "model-00001-of-00004.safetensors", "sha256": "24c52e6f7f486fc207f3604ef9d4b36b16a52c0deefaba0daffa04b494165aef" }, { "byte_size": 4999819552, "filename": "model-00002-of-00004.safetensors", "sha256": "467d79878aa623bd5582fd1d619eca71aa86b1bcf21438adc7e00c9aba895fee" }, { "byte_size": 4999802728, "filename": "model-00003-of-00004.safetensors", "sha256": "053256a99341de210629f17d86fa18371a34d617f4884ea0ec09d8e1d0411583" }, { "byte_size": 1035993232, "filename": "model-00004-of-00004.safetensors", "sha256": "7eb3a66fba088f3dba45d93a80f34751c1cdbdef2e4df2ca53063f97b38a4372" } ], "transformers_version": "4.44.2" }