104 lines
3.8 KiB
Python
Executable File
104 lines
3.8 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
Mass Dissection — All models on remote node
|
|
CSCI v1.0 — Cross-Scale Coherence Index
|
|
"""
|
|
import subprocess, os, sys, json, time
|
|
|
|
MODELS_DIR = "/mnt/models"
|
|
|
|
# Map GGUF filenames to organ directory names
|
|
models = {
|
|
"DeepSeek-R1-Distill-Qwen-14B-Q4_K_M.gguf": "deepseek-r1-14b",
|
|
"Qwen2.5-14B-Instruct-Q4_K_M.gguf": "qwen25-14b",
|
|
"gemma-2-9b-it-Q4_K_M.gguf": "gemma2-9b",
|
|
"Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf": "llama31-8b",
|
|
"Qwen2.5-7B-Instruct-Q4_K_M.gguf": "qwen25-7b",
|
|
"DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf": "deepseek-r1-distill-7b",
|
|
"DeepSeek-R1-7B-Q4_K_M.gguf": "deepseek-r1-7b",
|
|
"Mistral-7B-Instruct-v0.3-Q4_K_M.gguf": "mistral-7b",
|
|
"Phi-3.5-mini-instruct-Q4_K_M.gguf": "phi35-mini",
|
|
"Llama-3.2-3B-Instruct-Q4_K_M.gguf": "llama32-3b",
|
|
"Qwen2.5-3B-Instruct-Q4_K_M.gguf": "qwen25-3b",
|
|
"Llama-3.2-1B-Instruct-Q4_K_M.gguf": "llama32-1b",
|
|
"SmolLM2-135M-Instruct-Q8_0.gguf": "smollm2-135m",
|
|
}
|
|
|
|
results = []
|
|
skipped = []
|
|
|
|
for gguf, organ_name in models.items():
|
|
gguf_path = os.path.join(MODELS_DIR, gguf)
|
|
organ_path = os.path.join(ORGANS_DIR, organ_name)
|
|
|
|
if not os.path.exists(gguf_path):
|
|
print(f"[SKIP] {gguf} — not found")
|
|
skipped.append(gguf)
|
|
continue
|
|
|
|
if os.path.exists(os.path.join(organ_path, "manifest.json")):
|
|
# Already dissected — just measure
|
|
size_mb = sum(
|
|
os.path.getsize(os.path.join(dp, f))
|
|
for dp, dn, fn in os.walk(organ_path) for f in fn
|
|
) / (1024*1024)
|
|
print(f"[DONE] {organ_name} — already dissected ({size_mb:.0f}MB)")
|
|
results.append({"model": organ_name, "status": "exists", "size_mb": size_mb})
|
|
continue
|
|
|
|
# Dissect
|
|
print(f"\n{'='*60}")
|
|
print(f"[DISSECT] {gguf} → {organ_name}")
|
|
print(f"{'='*60}")
|
|
|
|
t0 = time.time()
|
|
r = subprocess.run(
|
|
["python3", EXTRACT, "--model", gguf_path, "--output", organ_path],
|
|
capture_output=True, text=True, timeout=600
|
|
)
|
|
elapsed = time.time() - t0
|
|
|
|
if r.returncode == 0:
|
|
# Get last lines (summary)
|
|
lines = r.stdout.strip().split("\n")
|
|
for line in lines[-10:]:
|
|
print(line)
|
|
|
|
size_mb = sum(
|
|
os.path.getsize(os.path.join(dp, f))
|
|
for dp, dn, fn in os.walk(organ_path) for f in fn
|
|
) / (1024*1024)
|
|
|
|
results.append({
|
|
"model": organ_name, "status": "dissected",
|
|
"size_mb": size_mb, "time_s": elapsed
|
|
})
|
|
print(f"[OK] {organ_name} — {size_mb:.0f}MB in {elapsed:.1f}s")
|
|
else:
|
|
print(f"[ERROR] {organ_name}")
|
|
print(r.stderr[-500:] if r.stderr else r.stdout[-500:])
|
|
results.append({"model": organ_name, "status": "error", "error": r.stderr[-200:]})
|
|
|
|
# Summary
|
|
print(f"\n{'='*60}")
|
|
print(f" MASS DISSECTION COMPLETE")
|
|
print(f"{'='*60}")
|
|
for r in results:
|
|
status = "✓" if r["status"] in ("dissected", "exists") else "✗"
|
|
size = f"{r.get('size_mb',0):.0f}MB"
|
|
time_s = f"{r.get('time_s',0):.0f}s" if r.get("time_s") else "cached"
|
|
print(f" {status} {r['model']:30s} {size:>8s} {time_s}")
|
|
|
|
total_mb = sum(r.get("size_mb",0) for r in results)
|
|
print(f"\n Total organs: {total_mb/1024:.1f} GB")
|
|
print(f"{'='*60}")
|
|
|
|
# Save results
|
|
json.dump(results, f, indent=2)
|
|
# ╔══ SALKA ELMADANI AUTHORSHIP CERTIFICATE ══╗
|
|
# © Salka Elmadani 2025-2026 — ALL RIGHTS RESERVED
|
|
# Licensed under Business Source License 1.1 — https://inference-x.com
|
|
# ─────────────────────────────────────────────────────────
|
|
# SIG-ED25519: XB8aA7wVzKOHkvMcZgE5YT3x8BUD/EwVTDRxEMSR7nmWYIT17XY+gC4AJ+y0B29l8MQGFDGk+buLoKxiagTFCA==
|
|
# VERIFY: python3 verify_authorship.py mass_dissect.py
|