f841dfaeed
Add TOPLOC honest-noise calibration storage/dispatch and validator divergence reporting for AH-021. Add opt-in HuggingFace marketplace pricing refresh, price-change history, CLI flags, and AH-023 tracking docs. Verification: .venv/bin/python -m pytest tests/ -q -k 'not integration' => 346 passed, 2 skipped, 1 deselected; compileall packages tests passed; focused AH-021/AH-023 tests 32 passed.
44 lines
1.4 KiB
JSON
44 lines
1.4 KiB
JSON
{
|
|
"models": {
|
|
"kimi-k2.7": {
|
|
"layers_start": 0,
|
|
"layers_end": 60,
|
|
"hf_repo": "unsloth/Kimi-K2.7-Code",
|
|
"aliases": [
|
|
"kimi-k2.7",
|
|
"Kimi-K2.7-Code",
|
|
"unsloth/Kimi-K2.7-Code"
|
|
],
|
|
"recommended": true,
|
|
"deployment_status": "recommended",
|
|
"hf_aliases": [],
|
|
"hf_verified_match_note": "Pending human curation (issue 23) — no HF inference-marketplace listing has been confirmed as a comparable params/quantization match for this preset yet. Leave empty until a human signs off; an empty hf_aliases list keeps this model on the static default price.",
|
|
"required_model_bytes": 638876385280,
|
|
"download_size_bytes": 638876385280,
|
|
"native_quantization": "int4",
|
|
"canonical_audit_dtype": "bfloat16",
|
|
"canonical_audit_quantization": "bfloat16",
|
|
"bytes_per_layer": {
|
|
"int4": 10473383366
|
|
},
|
|
"metadata": {
|
|
"architecture": "Mixture-of-Experts (MoE)",
|
|
"total_parameters": "1T",
|
|
"activated_parameters": "32B",
|
|
"num_layers": 61,
|
|
"context_length": 256000,
|
|
"native_quantization": "int4",
|
|
"canonical_audit_dtype": "bfloat16",
|
|
"canonical_audit_quantization": "bfloat16",
|
|
"download_size_gb": 595,
|
|
"recommended_short_name": "kimi-k2.7",
|
|
"recommended_engines": [
|
|
"vLLM",
|
|
"SGLang",
|
|
"KTransformers"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|