{
  "artifacts": [
    {
      "bytes": 15803475232,
      "filename": "Ling-3.0-tiny-BF16.gguf",
      "hub_introduced_in_commit": "5181b83cba18aa36484eb4f385479ddc015f37ea",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": null,
      "metadata_count": 55,
      "quantization": "BF16",
      "role": "model",
      "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "source_weights_manifest": "source-safetensors.sha256",
      "source_weights_manifest_sha256": "d8a7cf059fd4b4f2fd7f7d0b1118417be02f7b39a5c428461c027f5d71faff6d",
      "tensor_count": 526,
      "tensor_type_counts": {
        "BF16": 311,
        "F32": 215
      },
      "validation_reports": {
        "context": "validation/context-results.json",
        "generation": "validation/generation-BF16.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-BF16.json"
      }
    },
    {
      "bytes": 8408187744,
      "filename": "Ling-3.0-tiny-Q8_0.gguf",
      "hub_introduced_in_commit": "6ed6298b7b0b41c8db02d6773e6172e03745df55",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": null,
      "metadata_count": 55,
      "quantization": "Q8_0",
      "role": "model",
      "sha256": "326221bdef72525bd6178b072d3827cd5fb5248a55e8c44eb400417f401733bc",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q8_0": 311
      },
      "validation_reports": {
        "generation": "validation/generation-Q8_0.json",
        "kld": "validation/kld-results.json",
        "structure": "validation/structure-Q8_0.json"
      }
    },
    {
      "bytes": 6499262560,
      "filename": "Ling-3.0-tiny-Q6_K.gguf",
      "hub_introduced_in_commit": "b0d10c82afeb64ea0528ec4550c5b15a071ed4e4",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "Q6_K",
      "role": "model",
      "sha256": "480acd6ef2c664f026f1452548221a00954e9888393c6f49a425dd5567a3d77a",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q6_K": 305,
        "Q8_0": 6
      },
      "validation_reports": {
        "generation": "validation/generation-Q6_K.json",
        "kld": "validation/kld-results.json",
        "structure": "validation/structure-Q6_K.json"
      }
    },
    {
      "bytes": 5635443808,
      "filename": "Ling-3.0-tiny-Q5_K_M.gguf",
      "hub_introduced_in_commit": "d50633f06287cb120a9f9bd3d06843b08ab38c69",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "Q5_K_M",
      "role": "model",
      "sha256": "77d35bfd5ceaa03eff4d48af4438240f48ef4b6f5a70dff3cf25e78933b742ad",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q5_1": 6,
        "Q5_K": 272,
        "Q6_K": 33
      },
      "validation_reports": {
        "generation": "validation/generation-Q5_K_M.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-Q5_K_M.json"
      }
    },
    {
      "bytes": 4823895136,
      "filename": "Ling-3.0-tiny-Q4_K_M.gguf",
      "hub_introduced_in_commit": "4cb7775c71f0c269ced22d475118be72add13a5a",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "Q4_K_M",
      "role": "model",
      "sha256": "40e2d1201acdb346f4faa4cd8c2ce39b69d5fc9820baa17430ecd87cbdda7db5",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q4_K": 272,
        "Q5_0": 6,
        "Q6_K": 33
      },
      "validation_reports": {
        "context": "validation/context-results.json",
        "generation": "validation/generation-Q4_K_M.json",
        "imatrix_ablation": "validation/kld-Q4_K_M-ab.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "server": "validation/server-results.json",
        "structure": "validation/structure-Q4_K_M.json"
      }
    },
    {
      "bytes": 4554886240,
      "filename": "Ling-3.0-tiny-Q4_K_S.gguf",
      "hub_introduced_in_commit": "e0f51a846c7791455feb461910485f54fb7af091",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "Q4_K_S",
      "role": "model",
      "sha256": "b5688aee697a9129ee49616918d4411cdaca0b909c06820ba9300706cac22672",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q4_K": 295,
        "Q5_0": 6,
        "Q5_K": 9,
        "Q6_K": 1
      },
      "validation_reports": {
        "generation": "validation/generation-Q4_K_S.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-Q4_K_S.json"
      }
    },
    {
      "bytes": 4287511648,
      "filename": "Ling-3.0-tiny-IQ4_XS.gguf",
      "hub_introduced_in_commit": "a6fd141638d7aec1f3e06dc49e5efb64ee60d067",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "IQ4_XS",
      "role": "model",
      "sha256": "b81d3cc7d096e5ab2768191ea1de5549a9cc1efc87f20fba571e39f91e7a6f29",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "IQ4_NL": 6,
        "IQ4_XS": 304,
        "Q6_K": 1
      },
      "validation_reports": {
        "generation": "validation/generation-IQ4_XS.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-IQ4_XS.json"
      }
    },
    {
      "bytes": 3841570912,
      "filename": "Ling-3.0-tiny-Q3_K_M.gguf",
      "hub_introduced_in_commit": "e5b631e5990870b3b676f2aa5ca18f7af43aee2c",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "Q3_K_M",
      "role": "model",
      "sha256": "d32c6cbf24b736deb94c1d409dc4bf75f31aebf8822abb716772cb3352cd075f",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "Q3_K": 215,
        "Q4_0": 6,
        "Q4_K": 86,
        "Q5_K": 3,
        "Q6_K": 1
      },
      "validation_reports": {
        "generation": "validation/generation-Q3_K_M.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-Q3_K_M.json"
      }
    },
    {
      "bytes": 3556950112,
      "filename": "Ling-3.0-tiny-IQ3_M.gguf",
      "hub_introduced_in_commit": "c6cc27c2a5d176c30e7bf81b362e6310dc18a73d",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "IQ3_M",
      "role": "model",
      "sha256": "644a42f6c7680e2afcdd58258b39561df1eb858e4b8be7128c3677b5ba089198",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "IQ3_S": 257,
        "IQ4_NL": 6,
        "Q4_K": 47,
        "Q6_K": 1
      },
      "validation_reports": {
        "generation": "validation/generation-IQ3_M.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-IQ3_M.json"
      }
    },
    {
      "bytes": 2704009312,
      "filename": "Ling-3.0-tiny-IQ2_M.gguf",
      "hub_introduced_in_commit": "1db5044f7d3374c6cac5a29a507702341c07b98f",
      "hub_lfs_matches_local": true,
      "importance_matrix_sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "metadata_count": 59,
      "quantization": "IQ2_M",
      "role": "model",
      "sha256": "7f1fba0f96faf67fee40e9083070f753b3f8e484caf541b1b6bb91f786e2ddeb",
      "source_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526,
      "tensor_type_counts": {
        "F32": 215,
        "IQ2_S": 258,
        "IQ3_S": 28,
        "IQ4_NL": 6,
        "Q4_K": 18,
        "Q5_K": 1
      },
      "validation_reports": {
        "context": "validation/context-results.json",
        "generation": "validation/generation-IQ2_M.json",
        "kld": "validation/kld-results.json",
        "multiple_choice": "validation/multiple-choice-results.json",
        "structure": "validation/structure-IQ2_M.json"
      }
    },
    {
      "bytes": 44016768,
      "filename": "Ling-3.0-tiny-imatrix.gguf",
      "hub_introduced_in_commit": "92a3e7cc9566cbc5a66bcff32c0bad4fb3c4e9b5",
      "hub_lfs_matches_local": true,
      "matrix_entries": 332,
      "quantization": null,
      "role": "importance_matrix",
      "sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
      "tensor_count": 664,
      "validation_reports": {
        "inspection": "validation/imatrix.json"
      }
    }
  ],
  "conversion": {
    "bf16": {
      "bytes": 15803475232,
      "metadata_count": 55,
      "outtype": "bf16",
      "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "tensor_count": 526
    },
    "byte_reproduction_constraints": {
      "embedded_imatrix_path": "/tmp/Ling-3.0-tiny-imatrix.gguf",
      "embedded_primary_dataset_path": "/workspace/ling3/calibration/bartowski-imatrix-v5-semantic.txt",
      "embedded_supplement_dataset_path": "/workspace/ling3/calibration/eaddario/combined_all_micro.txt",
      "note": "Different path spellings change GGUF metadata bytes and therefore artifact SHA-256, even when tensor data is equivalent.",
      "source_directory_basename": "Ling-3.0-tiny"
    },
    "importance_matrix": {
      "collection": {
        "batch": 4096,
        "complete_chunks": 162,
        "context": 4096,
        "process_output": false,
        "tokens_processed": 663552,
        "trailing_tokens_excluded": 5338,
        "ubatch": 512
      },
      "embedded_metadata_limitation": "quantize.imatrix.dataset records only the first input; ordered_passes is authoritative.",
      "final": {
        "bytes": 44016768,
        "expert_slots": 8832,
        "expert_vectors": 69,
        "filename": "Ling-3.0-tiny-imatrix.gguf",
        "matrix_entries": 332,
        "sha256": "e8b15d131f9ce294f922c5c387f7a69829c12100d6a35bb1635a2b859083c3f0",
        "zero_expert_slots": 0
      },
      "format": "gguf",
      "ordered_passes": [
        {
          "bytes": 1496006,
          "complete_chunks": 89,
          "file": "bartowski-imatrix-v5-semantic.txt",
          "index": 1,
          "repository": "lemon07r/bartowski-imatrix-v5-semantic",
          "revision": "a306f203ee4323e0afe846ae02c2daafe17384d9",
          "serialized_lines": 6318,
          "sha256": "ff879b5a748f822ef539e43c596a3f44ab922f0295ee209d4220d9f86e86a063",
          "tokens_processed": 364544,
          "trailing_tokens_excluded": 1920
        },
        {
          "complete_chunks": 73,
          "extracted_bytes": 1008653,
          "extracted_file": "combined_all_micro.txt",
          "extracted_sha256": "fdb2d41abf04a2fb207502741a561a5a9ab385eb0c44a450eae676c410955946",
          "index": 2,
          "repository": "eaddario/imatrix-calibration",
          "revision": "e87ed55dcba9d9c3a3e41539f3e728e981b1daa4",
          "serialized_lines": 3130,
          "source_file": "combined_all_micro.parquet",
          "source_sha256": "94389921e1f67b180a99de28c3090b41ce6f1960eb13abad21b7eba7cbe11b26",
          "tokens_processed": 299008,
          "trailing_tokens_excluded": 3418
        }
      ],
      "primary_intermediate": {
        "bytes": 44016704,
        "sha256": "01e5d88e62b6654dacfe525908808911af103d06ec95a79ac2f78f36aa780dec"
      }
    },
    "quantization": {
      "all_outputs_direct_from_bf16": true,
      "allow_requantize": false,
      "base_sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e",
      "pure": false,
      "threads": 32
    }
  },
  "environment": {
    "compute_capability": "12.0",
    "container_image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
    "container_platform_manifest_digest": "sha256:4d1721e62b56d345c83b4fd6090664be6daf9312caab5b2e76f23d8231941851",
    "gpu": "NVIDIA RTX PRO 4500 Blackwell",
    "gpu_memory_mib": 32623,
    "kernel": "Linux 6.8.0-101-generic x86_64",
    "nvidia_driver": "580.126.20",
    "os": "Ubuntu 24.04.3 LTS",
    "provider": "RunPod Secure Cloud",
    "python_environments": {
      "converter": {
        "gguf_import_note": "convert_hf_to_gguf.py imported the vendored llama.cpp/gguf-py from the pinned repository because NO_LOCAL_GGUF was not set; the installed gguf package supplied inspection tooling.",
        "packages": {
          "gguf": "0.19.0",
          "huggingface_hub": "0.36.2",
          "numpy": "1.26.4",
          "protobuf": "4.25.9",
          "safetensors": "0.8.0",
          "sentencepiece": "0.2.2",
          "tokenizers": "0.22.2",
          "torch": "2.8.0+cu128",
          "tqdm": "4.70.0",
          "transformers": "4.57.6"
        },
        "purpose": "HF-to-GGUF conversion dependencies and GGUF inspection",
        "python": "3.12.3"
      },
      "hf_reference": {
        "packages": {
          "accelerate": "1.10.1",
          "huggingface_hub": "0.36.2",
          "numpy": "2.1.2",
          "safetensors": "0.8.0",
          "tokenizers": "0.22.2",
          "torch": "2.8.0+cu128",
          "tqdm": "4.70.0",
          "transformers": "4.57.6"
        },
        "purpose": "Transformers BF16 tokenizer and generation reference",
        "python": "3.12.3"
      },
      "utility_upload": {
        "packages": {
          "duckdb": "1.3.2",
          "huggingface_hub": "1.27.0",
          "numpy": "2.5.2",
          "protobuf": "7.35.1",
          "sentencepiece": "0.2.2",
          "tqdm": "4.70.0"
        },
        "purpose": "Calibration text extraction and Hub upload",
        "python": "3.12.3"
      }
    }
  },
  "independent_cross_checks": [
    {
      "exact_matches": [
        {
          "filename": "Ling-3.0-tiny-BF16.gguf",
          "sha256": "2020d58d44887c4078c310dad0363b2af0898a9ed6cc46675c0d23201833952e"
        },
        {
          "filename": "Ling-3.0-tiny-Q8_0.gguf",
          "sha256": "326221bdef72525bd6178b072d3827cd5fb5248a55e8c44eb400417f401733bc"
        }
      ],
      "relationship": "Post-hoc independent artifact comparison, not a weight source",
      "repository": "bloomer010/Ling-3.0-tiny-GGUF",
      "revision": "59820116411687d44e1333816609afca8c93aa0b"
    }
  ],
  "manifest_kind": "gguf_conversion",
  "release": {
    "date_utc": "2026-08-11",
    "license": "MIT",
    "publisher": "Mike0021",
    "repository": "Mike0021/Ling-3.0-tiny-GGUF",
    "repository_type": "model",
    "tag": "v1.0",
    "training_performed": false,
    "transformation": "BF16 GGUF conversion followed by direct post-training quantization"
  },
  "schema_version": "1.0.0",
  "source": {
    "control_file_sha256": {
      "chat_template.jinja": "eb6226c94ae38058f875d159f86a206b3a165828c0e7d6bda664ae14667f798a",
      "config.json": "9750d847957913f665a13c0b5a6537199e33c6f3ec970d9fcb55a0e5076d4012",
      "configuration_bailing_moe_v3.py": "f2c048966aec8a2f042cfeb1351f74d51a28589b409c55baae7d24e841c1f6c4",
      "generation_config.json": "64752c5973a55faf4cfc02604c7587c38b090f00013f91191f52362dcc79a4a8",
      "model.safetensors.index.json": "84ef9fe8ef967eeb0545deb1d23c0ce54e86e6b18fa943a7903d7354a79f9cf9",
      "modeling_bailing_moe_v3.py": "c2509bf7ac580c262e2581d34d6403aa21682d2e10beb9ad85ad8820a7e33a40",
      "special_tokens_map.json": "69b63b9f81044ead642d16a5fdc01bcc737dc1183746485c8397ab14d3126614",
      "tokenizer.json": "40fb9d7d7795b8bd305aeff39ce9963f3f450915b9553f2938e009be9a1fed60",
      "tokenizer_config.json": "2456b0372956cd3e82f17e33372148b115a94970bfd4878ba5e7e60cd3204f74"
    },
    "notes": [
      "model.safetensors.index.json metadata.total_size is not used as physical file size; measured shard bytes are authoritative."
    ],
    "repository": "inclusionAI/Ling-3.0-tiny",
    "required_directory_basename": "Ling-3.0-tiny",
    "revision": "a2ee06c0f2de5b171701aee7f73f70a1da75483b",
    "weights": {
      "actual_bytes": 15787992416,
      "format": "safetensors",
      "sha256_manifest": "source-safetensors.sha256",
      "sha256_manifest_sha256": "d8a7cf059fd4b4f2fd7f7d0b1118417be02f7b39a5c428461c027f5d71faff6d",
      "shard_count": 32,
      "weight_map_entries": 9283
    }
  },
  "toolchain": {
    "binary_sha256": {
      "llama-cli": "aa52b6f0281d85c65a35b0fd3aac786a0deb8a0d28f14bcb90352f93fad2e52e",
      "llama-completion": "cd16edd3ef2cfbc4ff5ea2ac1acd73a7f0e0355c4ad3c268e40ba9f85d039fe3",
      "llama-imatrix": "16e3fe106cd1832e3dd4aa03e954521e79f2fc58cd03afaa0953960a9f390006",
      "llama-perplexity": "78f36a12b0a823d0f7b9454151effd6ecb67387d8e57b59325e18de0362c2cc4",
      "llama-quantize": "eb98052b77b529891537ace9e35fed0ad6f0a8692d187213c8dc7e3be1d6eeb3",
      "llama-server": "6cba678338c0e81a6cb01e79a9bdae55007a2f246041f8af77d824bbf455ae71",
      "llama-tokenize": "d548bc241ac43bd6f05cec4b9b84ad01f43c2783d02641ec159c326a6ce9508e"
    },
    "build": {
      "build_type": "Release",
      "c_compiler": "GNU 13.3.0",
      "cmake": "3.28.3",
      "cuda_architectures_requested": "native",
      "cuda_architectures_resolved": [
        "sm_120a"
      ],
      "cuda_compiler": "12.8 build 35583870_0",
      "cxx_compiler": "GNU 13.3.0",
      "generator": "Ninja",
      "ggml_cuda": true,
      "ggml_native": false
    },
    "llama_cpp": {
      "build_number": 10372,
      "commit": "d8d862521e9ad842f2b47f3b392b039317782aa0",
      "convert_hf_to_gguf_sha256": "e38975e1c68d98ac1664dfd530616eb35c72294382a4dd873d4746b23f27779f",
      "repository": "https://github.com/aetherbird/llama.cpp.git",
      "required_ancestor_commits": [
        "517b467544f732ddabb3f7727932f8d004ad9457",
        "0266ebca66bd95b7a85d37b8ca08ccf9812b85cc"
      ],
      "upstream_pr": 26608,
      "worktree_clean": true
    }
  },
  "validation_inputs": {
    "kld": {
      "archive_sha256": "ef7edb566e3e2b2d31b29c1fdb0c89a4cc683597484c3dc2517919c615435a11",
      "batch": 512,
      "bf16_reference_bytes": 2565373716,
      "bf16_reference_sha256": "afa4dc9bd2d995dd85d8614494dc9cccec8e0e4bd6b2c24efc81d3bba96638f7",
      "chunks": 32,
      "context": 512,
      "repository": "ggml-org/ci",
      "revision": "927b3642933080f1b0e811e2f916e14c292992f9",
      "scored_tokens": 8160,
      "test_text_sha256": "173c87a53759e0201f33e0ccf978e510c2042d7f2cb78229d9a50d79b9e7dd08",
      "ubatch": 512
    },
    "multiple_choice": {
      "bytes": 762276,
      "file": "mmlu-validation.bin",
      "note": "The pinned tool log labels this path TruthfulQA; the input is MMLU validation.",
      "repository": "ikawrakow/validation-datasets-for-llama.cpp",
      "revision": "37884b81b4957f1950a53b6ff48d77c8dd5e430c",
      "seed": 1,
      "sha256": "470af3a74eccacfaf6f43b08aabf510f61e6c92fe20d17241ded934151e225fa",
      "tasks": 500
    }
  }
}