organ-architecture/assemble_935.py

#!/usr/bin/env python3
"""
Model 935 Assembler — Fixed organ header handling.
Reads source GGUF, replaces tensor DATA (skipping organ bin headers).
Z = dI/d(log s) · exp(iθ) — Signature 935
"""
import struct, sys, os, json

def read_organ_data_only(filepath):
    """Read organ bin, skip header, return only tensor data."""
    with open(filepath, "rb") as f:
        name_len = struct.unpack("<I", f.read(4))[0]
        f.read(name_len)  # skip name
        ndims = struct.unpack("<I", f.read(4))[0]
        for _ in range(ndims):
            f.read(8)  # skip dims
        f.read(4)  # skip dtype
        return f.read()  # pure tensor data

def main():
    if len(sys.argv) < 4:
        print("Usage: assemble_935.py <source.gguf> <organs_dir> <output.gguf>")
        sys.exit(1)
    
    source_gguf = sys.argv[1]
    organs_dir = sys.argv[2]
    output_gguf = sys.argv[3]
    
    f = open(source_gguf, "rb")
    magic = struct.unpack("<I", f.read(4))[0]
    version = struct.unpack("<I", f.read(4))[0]
    n_tensors = struct.unpack("<Q", f.read(8))[0]
    n_metadata = struct.unpack("<Q", f.read(8))[0]
    
    print(f"Source: {os.path.basename(source_gguf)}")
    print(f"  Version: {version}, Tensors: {n_tensors}, Metadata: {n_metadata}")
    
    def read_string():
        slen = struct.unpack("<Q", f.read(8))[0]
        return f.read(slen).decode("utf-8")
    
    def skip_value(vtype):
        sizes = {0:1, 1:1, 2:2, 3:2, 4:4, 5:4, 6:4, 7:1, 10:8, 11:8, 12:8}
        if vtype in sizes:
            f.read(sizes[vtype])
        elif vtype == 8:
            read_string()
        elif vtype == 9:
            arr_type = struct.unpack("<I", f.read(4))[0]
            arr_len = struct.unpack("<Q", f.read(8))[0]
            for _ in range(arr_len):
                skip_value(arr_type)
    
    for _ in range(n_metadata):
        read_string()
        vtype = struct.unpack("<I", f.read(4))[0]
        skip_value(vtype)
    
    tensor_info = []
    for _ in range(n_tensors):
        name = read_string()
        n_dims = struct.unpack("<I", f.read(4))[0]
        dims = [struct.unpack("<Q", f.read(8))[0] for _ in range(n_dims)]
        dtype = struct.unpack("<I", f.read(4))[0]
        offset = struct.unpack("<Q", f.read(8))[0]
        tensor_info.append({"name": name, "dims": dims, "dtype": dtype, "offset": offset})
    
    pos = f.tell()
    padding = (32 - (pos % 32)) % 32
    f.read(padding)
    data_start = f.tell()
    
    # Get file size
    f.seek(0, 2)
    file_end = f.tell()
    
    # Copy full header (everything before data_start)
    f.seek(0)
    header = f.read(data_start)
    
    # Build organ map (name -> filepath)
    organ_map = {}
    for category in ["skeleton", "organs", "embed", "norm", "adapters", "unknown"]:
        cat_dir = os.path.join(organs_dir, category)
        if os.path.isdir(cat_dir):
            for fname in os.listdir(cat_dir):
                if fname.endswith(".bin"):
                    tname = fname[:-4]  # remove .bin
                    organ_map[tname] = os.path.join(cat_dir, fname)
    
    print(f"  Organ files: {len(organ_map)}")
    print(f"  Header: {data_start} bytes")
    
    # Write output
    out = open(output_gguf, "wb")
    out.write(header)
    
    replaced = 0
    fallback = 0
    
    for i, ti in enumerate(tensor_info):
        name = ti["name"]
        safe_name = name.replace(".", "_")
        organ_path = organ_map.get(safe_name)
        
        # Calculate tensor size from GGUF offsets
        if i + 1 < len(tensor_info):
            tensor_size = tensor_info[i+1]["offset"] - ti["offset"]
        else:
            tensor_size = file_end - (data_start + ti["offset"])
        
        if organ_path and os.path.exists(organ_path):
            # Read organ data ONLY (skip header!)
            organ_data = read_organ_data_only(organ_path)
            
            if len(organ_data) == tensor_size:
                out.write(organ_data)
                replaced += 1
            else:
                # Size mismatch — fall back to source
                f.seek(data_start + ti["offset"])
                out.write(f.read(tensor_size))
                fallback += 1
                if abs(len(organ_data) - tensor_size) > 100:
                    print(f"  [MISMATCH] {name}: organ={len(organ_data)} vs gguf={tensor_size}")
        else:
            # No organ — use source
            f.seek(data_start + ti["offset"])
            out.write(f.read(tensor_size))
            fallback += 1
    
    out.close()
    f.close()
    
    final_size = os.path.getsize(output_gguf)
    source_size = os.path.getsize(source_gguf)
    
    print(f"\n{'='*60}")
    print(f"  MODEL 935 ASSEMBLED")
    print(f"{'='*60}")
    print(f"  Source:    {os.path.basename(source_gguf)} ({source_size/(1024**3):.2f} GB)")
    print(f"  Output:    {output_gguf} ({final_size/(1024**3):.2f} GB)")
    print(f"  Replaced:  {replaced} tensors from organs")
    print(f"  Fallback:  {fallback} tensors from source")
    print(f"  Size match: {'YES' if abs(final_size - source_size) < 1024 else 'NO — DELTA=' + str(final_size - source_size)}")
    print(f"  Signature: 935")
    print(f"{'='*60}")

if __name__ == "__main__":
    main()