{ "mic": "0.3", "name": "Granite causal LM", "usage": "AutoTokenizer + AutoModelForCausalLM, batched chat prompts, left padding, next-token logits and one SGD step", "architecture": "GraniteForCausalLM", "checkpoints": { "ibm-granite/granite-3.1-2b-instruct": { "fixture": "huggingface-mic/granite-3.1-2b-instruct-mic" } }, "fixtures": { "huggingface-mic/granite-3.1-2b-instruct-mic": { "built_from": "ibm-granite/granite-3.1-2b-instruct", "covers": [ "ibm-granite/granite-3.1-2b-instruct" ], "build": { "seed": 17, "model_class": "GraniteForCausalLM" } } }, "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": 20 }, "ibm-granite/granite-3.1-2b-instruct": { "devices": [ "cuda" ], "gpu_memory_gb": 16, "memory_gb": 16, "download_mb": 5000, "variants": { "bfloat16": { "gpu_memory_gb": 10 }, "default": { "devices": [] }, "eager": { "devices": [] } } } } } }, "outputs": { "runtime": { "compare": "exact" }, "logits.probe": { "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" } } }