{
  "mic": "0.3",
  "name": "MT5 seq2seq",
  "usage": "AutoTokenizer + AutoModelForSeq2SeqLM, batched translation-style prompts, right padding, inference and one SGD step",
  "architecture": "MT5ForConditionalGeneration",
  "checkpoints": {
    "google/mt5-small": {
      "fixture": "huggingface-mic/mt5-small-mic"
    }
  },
  "fixtures": {
    "huggingface-mic/mt5-small-mic": {
      "built_from": "google/mt5-small",
      "covers": [
        "google/mt5-small"
      ],
      "build": {
        "seed": 17,
        "model_class": "MT5ForConditionalGeneration"
      }
    }
  },
  "integrations": {
    "transformers": {
      "entry_point": "integrations/transformers/usage.md",
      "format": "runnable-markdown",
      "requires": [
        "transformers>=5",
        "torch"
      ],
      "targets": [
        "fixtures",
        "checkpoints"
      ],
      "variants": {
        "default": {},
        "eager": {
          "attn_implementation": "eager"
        },
        "bfloat16": {
          "dtype": "bfloat16"
        }
      },
      "training": true,
      "resources": {
        "fixture": {
          "memory_gb": 2,
          "download_mb": 40
        },
        "google/mt5-small": {
          "memory_gb": 4,
          "download_mb": 1200
        }
      }
    }
  },
  "outputs": {
    "runtime": {
      "compare": "exact"
    },
    "decoded_text": {
      "compare": "exact"
    },
    "probe_logits": {
      "compare": "allclose",
      "atol": 0.0001,
      "rtol": 0.0001
    },
    "training.loss": {
      "compare": "allclose",
      "atol": 0.0001,
      "rtol": 0.0001
    },
    "training.gradients": {
      "compare": "all_true"
    },
    "training.updated": {
      "compare": "true"
    }
  }
}