Track Kimi model metadata and cache path

packages/node/meshnet_node/model_catalog.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
+from pathlib import Path
 
 
 @dataclass
@@ -15,6 +16,7 @@ class ModelPreset:
     vram_int8: float
     vram_bf16: float
     description: str
+    metadata: dict | None = None
 
     def vram_for_quant(self, quant: str) -> float:
         """Return VRAM requirement in GB for the given quantization."""
@@ -123,6 +125,37 @@ CURATED_MODELS: list[ModelPreset] = [
         vram_bf16=16.0,
         description="DeepSeek's efficient MoE — strong coding + reasoning",
     ),
+    ModelPreset(
+        name="Kimi-K2.7-Code",
+        hf_repo="unsloth/Kimi-K2.7-Code",
+        num_layers=61,
+        vram_nf4=500.0,
+        vram_int8=1000.0,
+        vram_bf16=2000.0,
+        description="Moonshot/Unsloth coding-focused MoE model; 1T total, 32B activated",
+        metadata={
+            "architecture": "Mixture-of-Experts (MoE)",
+            "total_parameters": "1T",
+            "activated_parameters": "32B",
+            "num_layers": 61,
+            "dense_layers": 1,
+            "attention_hidden_dimension": 7168,
+            "moe_hidden_dimension_per_expert": 2048,
+            "attention_heads": 64,
+            "experts": 384,
+            "selected_experts_per_token": 8,
+            "shared_experts": 1,
+            "vocabulary_size": 160000,
+            "context_length": 256000,
+            "attention_mechanism": "MLA",
+            "activation_function": "SwiGLU",
+            "vision_encoder": "MoonViT",
+            "vision_encoder_parameters": "400M",
+            "license": "modified-mit",
+            "native_quantization": "int4",
+            "recommended_engines": ["vLLM", "SGLang", "KTransformers"],
+        },
+    ),
 ]
 
 
@@ -140,6 +173,44 @@ def detect_num_layers(hf_repo: str) -> int | None:
         return None
 
 
+def model_metadata_for(
+    hf_repo: str,
+    num_layers: int | None = None,
+    cache_dir: Path | None = None,
+) -> dict:
+    """Return operator-facing model metadata for a HuggingFace repo."""
+    for model in CURATED_MODELS:
+        if model.hf_repo == hf_repo:
+            metadata = dict(model.metadata or {})
+            metadata.setdefault("num_layers", model.num_layers)
+            return metadata
+
+    metadata: dict = {}
+    if num_layers is not None:
+        metadata["num_layers"] = num_layers
+    try:
+        from transformers import AutoConfig  # type: ignore[import]
+
+        cfg = AutoConfig.from_pretrained(
+            hf_repo,
+            cache_dir=str(cache_dir) if cache_dir is not None else None,
+        )
+        for attr, key in (
+            ("model_type", "architecture"),
+            ("num_hidden_layers", "num_layers"),
+            ("hidden_size", "hidden_size"),
+            ("num_attention_heads", "attention_heads"),
+            ("vocab_size", "vocabulary_size"),
+            ("max_position_embeddings", "context_length"),
+        ):
+            value = getattr(cfg, attr, None)
+            if value is not None:
+                metadata[key] = value
+    except Exception:
+        pass
+    return metadata
+
+
 def browse_hf_hub(top_n: int = 20) -> list[dict]:
     """Fetch top downloaded text-generation models from HuggingFace Hub."""
     try: