| { | |
| "mic": "0.3", | |
| "name": "InternVL3-1B", | |
| "usage": "AutoProcessor + AutoModelForImageTextToText, multimodal image+text inference and training", | |
| "architecture": "InternVLForConditionalGeneration", | |
| "checkpoints": { | |
| "OpenGVLab/InternVL3-1B-hf": { | |
| "fixture": "hf-internal-testing/mic-internvl-slim" | |
| } | |
| }, | |
| "fixtures": { | |
| "hf-internal-testing/mic-internvl-slim": { | |
| "built_from": "OpenGVLab/InternVL3-1B-hf", | |
| "covers": [ | |
| "OpenGVLab/InternVL3-1B-hf" | |
| ], | |
| "build": { | |
| "seed": 17 | |
| } | |
| } | |
| }, | |
| "integrations": { | |
| "transformers": { | |
| "entry_point": "integrations/transformers/usage.md", | |
| "format": "runnable-markdown", | |
| "requires": [ | |
| "transformers>=4.52", | |
| "torch", | |
| "Pillow", | |
| "numpy" | |
| ], | |
| "targets": [ | |
| "fixtures" | |
| ], | |
| "variants": { | |
| "default": {}, | |
| "eager": { | |
| "attn_implementation": "eager" | |
| }, | |
| "bfloat16": { | |
| "dtype": "bfloat16" | |
| } | |
| }, | |
| "training": true, | |
| "resources": { | |
| "fixture": { | |
| "memory_gb": 4, | |
| "download_mb": 200 | |
| }, | |
| "OpenGVLab/InternVL3-1B-hf": { | |
| "memory_gb": 8, | |
| "download_mb": 2100 | |
| } | |
| } | |
| } | |
| }, | |
| "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" | |
| } | |
| } | |
| } | |