embeddinggemma-2-GGUF / PUBLISHED_VALIDATION.json
homerquan's picture
Record published Docker pull and multimodal validation
d122027 verified
Raw History Blame Contribute Delete
4.43 kB
{
"verified_utc": "2026-11-01T15:12:30.091924+00:00",
"artifact_revision": "336c50f403d3b98df6b58de1a96e71e26cbcbb06",
"public_checksums": {
"passed": true,
"public": true,
"repository": "MirrorNeuronLab/embeddinggemma-2-GGUF",
"revision": "336c50f403d3b98df6b58de1a96e71e26cbcbb06",
"files_checked": [
".gitattributes",
"GGUF_AUDIT.json",
"LICENSE",
"PROVENANCE.json",
"README.md",
"SOURCE_SHA256SUMS",
"TIMINGS.json",
"VALIDATION.json",
"embeddinggemma-2-Q4_K_M.gguf",
"mmproj-embeddinggemma-2-Q8_0.gguf",
"reproduce/logs/requirements-lock.txt",
"reproduce/scripts/audit_gguf.py",
"reproduce/scripts/convert_compatible.py",
"reproduce/scripts/download_source.py",
"reproduce/scripts/reproduce.sh",
"reproduce/scripts/run_step.py",
"reproduce/scripts/start_validation_runner.sh",
"reproduce/scripts/validate_bf16.py",
"reproduce/scripts/validate_dmr.py",
"reproduce/scripts/validation_common.py"
],
"method": "Public unauthenticated HTTPS reads for metadata; LFS SHA-256 and byte sizes for binaries; full remote content SHA-256 for remaining release files."
},
"docker_pull": {
"stage": "hf-dmr-pull",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"pull",
"hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:33.079233+00:00",
"finished_utc": "2026-11-01T15:10:41.337838+00:00",
"elapsed_seconds": 8.258602988003986,
"returncode": 0
},
"docker_model_run": {
"stage": "hf-dmr-run",
"command": [
"env",
"MODEL_RUNNER_HOST=http://127.0.0.1:12435",
"docker",
"model",
"run",
"--detach",
"hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M"
],
"cwd": "$TASK_ROOT",
"started_utc": "2026-11-01T15:10:41.357601+00:00",
"finished_utc": "2026-11-01T15:10:42.909069+00:00",
"elapsed_seconds": 1.5514679400075693,
"returncode": 0
},
"docker_embeddings": {
"passed": true,
"model": "hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M",
"endpoint": "http://127.0.0.1:12435/engines/llama.cpp/v1/embeddings",
"text": {
"http_status": 200,
"elapsed_seconds": 1.768582244985737,
"vectors": 4,
"dimensions": 768,
"finite": true,
"l2_norms": [
0.9999999906183037,
0.9999999717982236,
0.9999999449210023,
0.9999999732160483
],
"related_cosine": 0.8650823975051903,
"unrelated_cosine": 0.5486270130835971
},
"repeat": {
"http_status": 200,
"elapsed_seconds": 0.027495156013173983,
"vectors": 4,
"dimensions": 768,
"finite": true,
"l2_norms": [
0.9999999906183037,
0.9999999717982236,
0.9999999449210023,
0.9999999732160483
],
"max_abs_difference": 0.0
},
"cosine_to_bf16_text": [
0.9941200584690152,
0.9908234124220315,
0.9889631445265419,
0.9972267675976894
],
"image": {
"http_status": 200,
"elapsed_seconds": 0.09476551102125086,
"vectors": 1,
"dimensions": 768,
"finite": true,
"l2_norms": [
1.0000000458974723
]
},
"audio": {
"http_status": 200,
"elapsed_seconds": 0.033992818993283436,
"vectors": 1,
"dimensions": 768,
"finite": true,
"l2_norms": [
1.0000000058851288
]
},
"mixed_batch": {
"http_status": 200,
"elapsed_seconds": 0.06493666299502365,
"vectors": 3,
"dimensions": 768,
"finite": true,
"l2_norms": [
0.9999999906183037,
1.0000000458974723,
1.0000000058851288
]
},
"scope": "Functional smoke checks on four texts, one solid-color image, and one synthetic audio tone. Not a retrieval or multimodal quality benchmark."
},
"documented_configuration": {
"http_status": 200,
"elapsed_seconds": 1.6663787690049503,
"vectors": 1,
"dimensions": 768,
"finite": true,
"l2_norms": [
0.9999999906183037
]
},
"automatic_projector_selection": "Verified by pulling :Q4_K_M from Hugging Face without specifying an mmproj path and successfully requesting image/audio/mixed embeddings."
}