82 lines
3.3 KiB
Python
82 lines
3.3 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
MODEL 935 v2 — Correct graft: only FFN organs, preserve attention+embed alignment
|
|
Base: DeepSeek-R1-Distill-7B (R1 reasoning skeleton + embeddings intact)
|
|
Graft: Qwen2.5-7B FFN organs only (knowledge)
|
|
|
|
Z = dI/d(log s) · exp(iθ) — Signature 935
|
|
"""
|
|
import os, json, shutil
|
|
ORGANS = "/root/organ-architecture/organs"
|
|
OUTPUT = os.path.join(ORGANS, "model-935-v2")
|
|
|
|
if os.path.exists(OUTPUT):
|
|
shutil.rmtree(OUTPUT)
|
|
|
|
# Base: DeepSeek-R1-Distill-7B (complete, unmodified)
|
|
base = os.path.join(ORGANS, "deepseek-r1-distill-7b")
|
|
print("[1/3] Base: DeepSeek-R1-Distill-7B (complete)")
|
|
shutil.copytree(base, OUTPUT)
|
|
|
|
# Graft: Only FFN weights from Qwen2.5-7B (NOT norms, NOT attention, NOT embed)
|
|
qwen_organs = os.path.join(ORGANS, "qwen25-7b", "organs")
|
|
out_organs = os.path.join(OUTPUT, "organs")
|
|
|
|
grafted = 0
|
|
skipped = 0
|
|
|
|
for fname in os.listdir(qwen_organs):
|
|
if not fname.endswith('.bin'):
|
|
continue
|
|
# Only graft actual FFN weights: ffn_down, ffn_gate, ffn_up
|
|
# Skip ffn_norm (must stay with base skeleton for alignment)
|
|
is_ffn_weight = any(x in fname for x in ['ffn_down', 'ffn_gate', 'ffn_up'])
|
|
is_ffn_norm = 'ffn_norm' in fname
|
|
|
|
if is_ffn_weight and not is_ffn_norm:
|
|
src = os.path.join(qwen_organs, fname)
|
|
dst = os.path.join(out_organs, fname)
|
|
if os.path.exists(dst):
|
|
src_size = os.path.getsize(src)
|
|
dst_size = os.path.getsize(dst)
|
|
if src_size == dst_size: # Compatible dimensions
|
|
shutil.copy2(src, dst)
|
|
grafted += 1
|
|
else:
|
|
skipped += 1
|
|
print(f" [DIM MISMATCH] {fname}: {src_size} vs {dst_size}")
|
|
else:
|
|
skipped += 1
|
|
|
|
print(f"\n[2/3] Grafted {grafted} FFN tensors from Qwen2.5-7B")
|
|
print(f" Skipped: {skipped}")
|
|
|
|
# Update manifest
|
|
manifest = json.load(open(os.path.join(OUTPUT, "manifest.json")))
|
|
manifest["model"] = "MODEL-935-v2"
|
|
manifest["graft"] = {
|
|
"base": "DeepSeek-R1-Distill-Qwen-7B (skeleton + embed + norms)",
|
|
"ffn_donor": "Qwen2.5-7B-Instruct (FFN weights only: down/gate/up)",
|
|
"method": "Selective organ graft — preserve attention↔embed alignment",
|
|
"equation": "Z = dI/d(log s) · exp(iθ)",
|
|
"principle": "R1 reasoning + Qwen knowledge, zero alignment friction",
|
|
"signature": 935
|
|
}
|
|
with open(os.path.join(OUTPUT, "manifest.json"), "w") as f:
|
|
json.dump(manifest, f, indent=2)
|
|
|
|
total = sum(1 for _,_,f in os.walk(OUTPUT) for _ in f if _.endswith('.bin'))
|
|
size = sum(os.path.getsize(os.path.join(dp,f)) for dp,_,fn in os.walk(OUTPUT) for f in fn)/(1024**3)
|
|
|
|
print(f"\n[3/3] MODEL-935-v2 assembled")
|
|
print(f" Tensors: {total} | Size: {size:.2f} GB")
|
|
print(f" Grafted FFN: {grafted} | Base preserved: {total - grafted}")
|
|
print(f" Signature: 935")
|
|
# ╔══ SALKA ELMADANI AUTHORSHIP CERTIFICATE ══╗
|
|
# © Salka Elmadani 2025-2026 — ALL RIGHTS RESERVED
|
|
# Licensed under Business Source License 1.1 — https://inference-x.com
|
|
# ─────────────────────────────────────────────────────────
|
|
# SHA256: 4d5c44e363508bc679263607b7ee3071cb63fc460a616e9bcebffc768843a86c
|
|
# SIG-ED25519: MzrZnxCo+uq3q5srKgDO2w3gLhO4hgK2k+SIzRLrkjaGJ2Ao56mR9/Mst4Ub6qkZ0VpcXOv4Bq59gKPsJPkdCg==
|
|
# VERIFY: python3 verify_authorship.py build_935_v2.py
|