emilandClaude Opus 4.7
75c9ee4576
C++ core (libmemba.so): - include/memba/state.h — C API (state_new/free/save/load/get_size) - src/state.cpp — MEMB file format: magic, version, SHA-256 model_id, CRC-32, opaque llama_state_*_data() blob - src/cli.cpp — minimal demo binary with greedy sampler - CMakeLists.txt + build.sh with llama.cpp submodule, CUDA auto-detect Python SDK (memba): - core.py — file I/O via llama-cpp-python's exposed C functions, unwraps _LlamaContext to access raw context pointer (≥0.3.x) - session.py — high-level Session with auto-save/load, ChatML wrapper for instruct models, raw mode for base models - cli.py — typer-based: chat (REPL), run (one-shot), list, rm, info Examples: - 01_basic_save_load.py, 02_chat_session.py Experiments (throwaway POCs documenting product-direction findings): - recall_poc.py — git log → state → cross-process query - mood_poc.py — batch sentiment trajectory, Mamba vs Transformer - mood_stream_poc.py, mood_batch_poc.py — variants - diag_saveload.py — minimal save/load isolation test - README.md documents the headline finding: save/load is byte-identical, but Falcon-Mamba-7B-Instruct does not retain facts across conversation turns even in-process — limits viable products to single-prompt analysis and persona priming. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
"""
|
|
Diagnostic: does the model retain context AFTER save in the SAME process,
|
|
and AFTER load in a fresh process? Compares three scenarios.
|
|
"""
|
|
import sys, argparse
|
|
from pathlib import Path
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "python"))
|
|
from llama_cpp import Llama
|
|
from memba import core
|
|
|
|
MODEL = "/home/emil/Desktop/Coding/AI/Memba/falcon-mamba-7B-instruct-Q4_K_M.gguf"
|
|
STATE = "/tmp/diag_saveload.memb"
|
|
|
|
INGEST = "I'm telling you a secret. My pet hamster is named Bartholomew. He is 4 years old. Reply 'ok'."
|
|
QUERY = "What is the name of my pet?"
|
|
|
|
|
|
def chatml(msg):
|
|
return f"<|im_start|>user\n{msg}<|im_end|>\n<|im_start|>assistant\n"
|
|
|
|
|
|
def make_llama():
|
|
return Llama(model_path=MODEL, n_ctx=2048, n_gpu_layers=-1, verbose=False)
|
|
|
|
|
|
def ask(m, prompt):
|
|
out = m(chatml(prompt), max_tokens=60, stop=["<|im_end|>"], echo=False)
|
|
return out["choices"][0]["text"].strip()
|
|
|
|
|
|
def build():
|
|
m = make_llama()
|
|
ack = ask(m, INGEST)
|
|
print(f" [build] ack: {ack!r}")
|
|
print(f" [build] state size (live): {core.get_state_size(m):,} B")
|
|
# In-process query BEFORE saving
|
|
print(f" [build] in-proc query BEFORE save: {ask(m, QUERY)!r}")
|
|
# Save
|
|
core.save_state(m, MODEL, STATE)
|
|
print(f" [build] state saved")
|
|
# In-process query AFTER saving (should still work — save shouldn't mutate)
|
|
print(f" [build] in-proc query AFTER save: {ask(m, QUERY)!r}")
|
|
|
|
|
|
def query():
|
|
m = make_llama()
|
|
print(f" [query] before load — fresh model: {ask(m, QUERY)!r}")
|
|
core.load_state(m, MODEL, STATE)
|
|
print(f" [query] state size after load: {core.get_state_size(m):,} B")
|
|
print(f" [query] after load: {ask(m, QUERY)!r}")
|
|
# Try a second time in case position is wonky
|
|
print(f" [query] second ask: {ask(m, QUERY)!r}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
cmd = sys.argv[1] if len(sys.argv) > 1 else "build"
|
|
{"build": build, "query": query}[cmd]()
|