{ "mic": "0.3", "name": "Falcon causal LM", "usage": "AutoTokenizer + AutoModelForCausalLM, batched left-padded prompts, seeded SGD step", "architecture": "FalconForCausalLM", "checkpoints": { "tiiuae/falcon-7b": { "fixture": "huggingface-mic/falcon-7b-mic" } }, "fixtures": { "huggingface-mic/falcon-7b-mic": { "built_from": "tiiuae/falcon-7b", "covers": [ "tiiuae/falcon-7b" ], "build": { "seed": 17, "model_class": "FalconForCausalLM" } } }, "integrations": { "transformers": { "entry_point": "integrations/transformers/usage.md", "format": "runnable-markdown", "requires": [ "transformers>=5", "torch" ], "targets": [ "fixtures" ], "variants": { "default": {}, "eager": { "attn_implementation": "eager" }, "bfloat16": { "dtype": "bfloat16" } }, "training": true, "resources": { "fixture": { "memory_gb": 2, "download_mb": 40 }, "tiiuae/falcon-7b": { "devices": [ "cuda" ], "gpus": 1, "gpu_memory_gb": 22, "memory_gb": 32, "download_mb": 14000, "variants": { "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" } } }