{ "mic": "0.3", "name": "GLM-OCR image-to-text", "usage": "AutoProcessor + AutoModelForImageTextToText, chat template, batched images, causal-LM labels", "architecture": "GlmOcrForConditionalGeneration", "checkpoints": { "zai-org/GLM-OCR": { "fixture": "huggingface-mic/GLM-OCR-mic" } }, "fixtures": { "huggingface-mic/GLM-OCR-mic": { "built_from": "zai-org/GLM-OCR", "covers": [ "zai-org/GLM-OCR" ], "build": { "seed": 17, "model_class": "GlmOcrForConditionalGeneration" } } }, "integrations": { "transformers": { "entry_point": "integrations/transformers/usage.md", "format": "runnable-markdown", "requires": [ "transformers>=5", "torch", "pillow", "torchvision" ], "targets": [ "fixtures", "checkpoints" ], "variants": { "default": {}, "eager": { "attn_implementation": "eager" }, "bfloat16": { "dtype": "bfloat16" } }, "training": true, "resources": { "fixture": { "memory_gb": 4, "download_mb": 60 }, "zai-org/GLM-OCR": { "devices": [ "cuda" ], "memory_gb": 32, "gpu_memory_gb": 16, "download_mb": 4000, "variants": { "bfloat16": { "gpu_memory_gb": 8 }, "default": { "devices": [] }, "eager": { "devices": [] } } } } } }, "outputs": { "runtime": { "compare": "exact" }, "predicted_tokens": { "compare": "exact" }, "answer_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" } } }