File size: 1,682 Bytes
0a967e6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | {
"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"
}
}
}
|