{ "base_model": "GSAI-ML/LLaDA-8B-Instruct", "base_revision": "08b83a6feb34df1a6011b80c3c00c7563e963b07", "delimiter_tokens": [ "|design-start|", "|design-end|", "|label-start|", "|label-end|" ], "exported_model_directory": "DiBO-AntMorphology", "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": "39e5b6e3f3c48d7d2623f7f5fd4e6b0b47e2f9660d799c85affaa7be80aaf212", "parsed_design": [ -0.003000000026077032, 0.014000000432133675, 0.004999999888241291, 3.3329999446868896, -0.746999979019165, 5.367000102996826, 0.10899999737739563, 3.121999979019165, -1.7660000324249268, 30.04400062561035, 55.465999603271484, 20.36199951171875, 0.19699999690055847, 0.20600000023841858, 0.41100001335144043, 0.0, 0.0020000000949949026, -0.00800000037997961, 10.708000183105469, -9.699999809265137, 78.87699890136719, -2.7070000171661377, 5.23199987411499, -2.01200008392334, 27.340999603271484, 57.8489990234375, 17.358999252319336, 0.19300000369548798, 0.2150000035762787, 0.37700000405311584, -0.0010000000474974513, -0.0, 0.012000000104308128, -2.243000030517578, 4.783999919891357, 179.83999633789062, 0.8889999985694885, 9.090999603271484, -4.223999977111816, 30.07900047302246, 59.779998779296875, 23.56399917602539, 0.18700000643730164, 0.18199999630451202, 0.3619999885559082, 0.004999999888241291, -0.01899999938905239, -0.0010000000474974513, -0.7429999709129333, -11.560999870300293, -93.50700378417969, -0.32899999618530273, 6.230000019073486, -13.532999992370605, 30.777000427246094, 78.61900329589844, 19.349000930786133, 0.18000000715255737, 0.20499999821186066, 0.34200000762939453 ], "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, 19, 2129, 20479, 14 ] ], "dtype": "bfloat16", "sha256": "4ead06694a30b74019cd077f8d968ab14f3133298095a81cc84c103c102427f8", "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": "39e5b6e3f3c48d7d2623f7f5fd4e6b0b47e2f9660d799c85affaa7be80aaf212", "parsed_design": [ -0.003000000026077032, 0.014000000432133675, 0.004999999888241291, 3.3329999446868896, -0.746999979019165, 5.367000102996826, 0.10899999737739563, 3.121999979019165, -1.7660000324249268, 30.04400062561035, 55.465999603271484, 20.36199951171875, 0.19699999690055847, 0.20600000023841858, 0.41100001335144043, 0.0, 0.0020000000949949026, -0.00800000037997961, 10.708000183105469, -9.699999809265137, 78.87699890136719, -2.7070000171661377, 5.23199987411499, -2.01200008392334, 27.340999603271484, 57.8489990234375, 17.358999252319336, 0.19300000369548798, 0.2150000035762787, 0.37700000405311584, -0.0010000000474974513, -0.0, 0.012000000104308128, -2.243000030517578, 4.783999919891357, 179.83999633789062, 0.8889999985694885, 9.090999603271484, -4.223999977111816, 30.07900047302246, 59.779998779296875, 23.56399917602539, 0.18700000643730164, 0.18199999630451202, 0.3619999885559082, 0.004999999888241291, -0.01899999938905239, -0.0010000000474974513, -0.7429999709129333, -11.560999870300293, -93.50700378417969, -0.32899999618530273, 6.230000019073486, -13.532999992370605, 30.777000427246094, 78.61900329589844, 19.349000930786133, 0.18000000715255737, 0.20499999821186066, 0.34200000762939453 ], "valid": true }, "source_config_class": "LLaDAConfig", "source_dtype_counts": { "bfloat16": 8015126528 }, "source_forward": { "argmax": [ [ 5998, 25, 198, 19, 2129, 20479, 14 ] ], "dtype": "bfloat16", "sha256": "4ead06694a30b74019cd077f8d968ab14f3133298095a81cc84c103c102427f8", "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": 0.6102560758590698, "norm_mean": 0.6102560758590698, "norm_median": 0.6102560758590698, "norm_top10_avg": 0.6102560758590698, "norm_top20_avg": 0.6102560758590698, "norm_top5_avg": 0.6102560758590698, "raw_max": 209.40826416015625, "raw_mean": 209.40826416015625, "raw_median": 209.40826416015625, "raw_top10_avg": 209.40826416015625, "raw_top20_avg": 209.40826416015625, "raw_top5_avg": 209.40826416015625 }, "valid_candidates": 1 }, "parity": true, "ran": true, "source": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.6102560758590698, "norm_mean": 0.6102560758590698, "norm_median": 0.6102560758590698, "norm_top10_avg": 0.6102560758590698, "norm_top20_avg": 0.6102560758590698, "norm_top5_avg": 0.6102560758590698, "raw_max": 209.40826416015625, "raw_mean": 209.40826416015625, "raw_median": 209.40826416015625, "raw_top10_avg": 209.40826416015625, "raw_top20_avg": 209.40826416015625, "raw_top5_avg": 209.40826416015625 }, "valid_candidates": 1 } }, "tensor_dtype_match": true, "tensor_shape_match": true, "tensor_value_match": true, "tokenizer_match": true }, "remote": { "downloaded_checkpoint": "dibo_ant_morphology_final.pt", "from_pretrained": true, "pt_hash_match": true, "repository_id": "zpointsun/DiBO-AntMorphology", "revision": "5ff202c22f9c9c81b91d9bfdf6485193c5b3b75a", "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": "39e5b6e3f3c48d7d2623f7f5fd4e6b0b47e2f9660d799c85affaa7be80aaf212", "parsed_design": [ -0.003000000026077032, 0.014000000432133675, 0.004999999888241291, 3.3329999446868896, -0.746999979019165, 5.367000102996826, 0.10899999737739563, 3.121999979019165, -1.7660000324249268, 30.04400062561035, 55.465999603271484, 20.36199951171875, 0.19699999690055847, 0.20600000023841858, 0.41100001335144043, 0.0, 0.0020000000949949026, -0.00800000037997961, 10.708000183105469, -9.699999809265137, 78.87699890136719, -2.7070000171661377, 5.23199987411499, -2.01200008392334, 27.340999603271484, 57.8489990234375, 17.358999252319336, 0.19300000369548798, 0.2150000035762787, 0.37700000405311584, -0.0010000000474974513, -0.0, 0.012000000104308128, -2.243000030517578, 4.783999919891357, 179.83999633789062, 0.8889999985694885, 9.090999603271484, -4.223999977111816, 30.07900047302246, 59.779998779296875, 23.56399917602539, 0.18700000643730164, 0.18199999630451202, 0.3619999885559082, 0.004999999888241291, -0.01899999938905239, -0.0010000000474974513, -0.7429999709129333, -11.560999870300293, -93.50700378417969, -0.32899999618530273, 6.230000019073486, -13.532999992370605, 30.777000427246094, 78.61900329589844, 19.349000930786133, 0.18000000715255737, 0.20499999821186066, 0.34200000762939453 ], "valid": true }, "export_config_auto_map": { "AutoConfig": "zpointsun/DiBO-AntMorphology--configuration_llada.LLaDAConfig", "AutoModel": "zpointsun/DiBO-AntMorphology--modeling_dibo_llada.DiBOLLaDAModelLM", "AutoModelForCausalLM": "zpointsun/DiBO-AntMorphology--modeling_dibo_llada.DiBOLLaDAModelLM" }, "export_config_class": "LLaDAConfig", "export_forward": { "argmax": [ [ 5998, 25, 198, 19, 2129, 20479, 14 ] ], "dtype": "bfloat16", "sha256": "4ead06694a30b74019cd077f8d968ab14f3133298095a81cc84c103c102427f8", "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": "39e5b6e3f3c48d7d2623f7f5fd4e6b0b47e2f9660d799c85affaa7be80aaf212", "parsed_design": [ -0.003000000026077032, 0.014000000432133675, 0.004999999888241291, 3.3329999446868896, -0.746999979019165, 5.367000102996826, 0.10899999737739563, 3.121999979019165, -1.7660000324249268, 30.04400062561035, 55.465999603271484, 20.36199951171875, 0.19699999690055847, 0.20600000023841858, 0.41100001335144043, 0.0, 0.0020000000949949026, -0.00800000037997961, 10.708000183105469, -9.699999809265137, 78.87699890136719, -2.7070000171661377, 5.23199987411499, -2.01200008392334, 27.340999603271484, 57.8489990234375, 17.358999252319336, 0.19300000369548798, 0.2150000035762787, 0.37700000405311584, -0.0010000000474974513, -0.0, 0.012000000104308128, -2.243000030517578, 4.783999919891357, 179.83999633789062, 0.8889999985694885, 9.090999603271484, -4.223999977111816, 30.07900047302246, 59.779998779296875, 23.56399917602539, 0.18700000643730164, 0.18199999630451202, 0.3619999885559082, 0.004999999888241291, -0.01899999938905239, -0.0010000000474974513, -0.7429999709129333, -11.560999870300293, -93.50700378417969, -0.32899999618530273, 6.230000019073486, -13.532999992370605, 30.777000427246094, 78.61900329589844, 19.349000930786133, 0.18000000715255737, 0.20499999821186066, 0.34200000762939453 ], "valid": true }, "source_config_class": "LLaDAConfig", "source_dtype_counts": { "bfloat16": 8015126528 }, "source_forward": { "argmax": [ [ 5998, 25, 198, 19, 2129, 20479, 14 ] ], "dtype": "bfloat16", "sha256": "4ead06694a30b74019cd077f8d968ab14f3133298095a81cc84c103c102427f8", "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": 0.6102560758590698, "norm_mean": 0.6102560758590698, "norm_median": 0.6102560758590698, "norm_top10_avg": 0.6102560758590698, "norm_top20_avg": 0.6102560758590698, "norm_top5_avg": 0.6102560758590698, "raw_max": 209.40826416015625, "raw_mean": 209.40826416015625, "raw_median": 209.40826416015625, "raw_top10_avg": 209.40826416015625, "raw_top20_avg": 209.40826416015625, "raw_top5_avg": 209.40826416015625 }, "valid_candidates": 1 }, "parity": true, "ran": true, "source": { "candidate_count": 1, "statistics": { "n": 1.0, "norm_max": 0.6102560758590698, "norm_mean": 0.6102560758590698, "norm_median": 0.6102560758590698, "norm_top10_avg": 0.6102560758590698, "norm_top20_avg": 0.6102560758590698, "norm_top5_avg": 0.6102560758590698, "raw_max": 209.40826416015625, "raw_mean": 209.40826416015625, "raw_median": 209.40826416015625, "raw_top10_avg": 209.40826416015625, "raw_top20_avg": 209.40826416015625, "raw_top5_avg": 209.40826416015625 }, "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": "ant__legacy_old__rl_step128.pt", "source_checkpoint_sha256": "c8b00d953babae2265d021513317e5207174b72f857ee6291a2fc08fdb535c5d", "source_checkpoint_size": 16030379937, "task": "AntMorphology-Exact-v0", "torch_version": "2.6.0+cu118", "transformers_export_weights": [ { "byte_size": 4994672360, "filename": "model-00001-of-00004.safetensors", "sha256": "953ba14fdb624fc2a7cb5d60971c9011e49f8e56682f0f0c28f6653fccb90153" }, { "byte_size": 4999819552, "filename": "model-00002-of-00004.safetensors", "sha256": "96fa552402f7d1b12aed2a6d58f9df5d27c2104dbd7f21d58f3f2de429466c09" }, { "byte_size": 4999802728, "filename": "model-00003-of-00004.safetensors", "sha256": "b758ae75141dd6b469910d3f15b9d94ca26a2e66ddf953d671c58ba53c6d2103" }, { "byte_size": 1035993232, "filename": "model-00004-of-00004.safetensors", "sha256": "01fdd5380f64ddefb26ed9b0d2ef09d91e2e3239a4aa753a26ca57a38b0f86be" } ], "transformers_version": "4.44.2" }