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>
68 lines
2.8 KiB
Python
68 lines
2.8 KiB
Python
"""
|
|
01_basic_save_load.py — save and load SSM state with the low-level core API.
|
|
|
|
Run:
|
|
python examples/01_basic_save_load.py --model path/to/falcon-mamba-7b-Q4_K_M.gguf
|
|
"""
|
|
|
|
import argparse
|
|
import sys
|
|
from pathlib import Path
|
|
from llama_cpp import Llama
|
|
from memba import core
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--model", required=True, help="Path to GGUF file")
|
|
parser.add_argument("--gpu-layers", type=int, default=0, help="GPU layers (0=CPU)")
|
|
parser.add_argument("--state", default="/tmp/demo.memb", help="State file path")
|
|
args = parser.parse_args()
|
|
|
|
# ── Load model ───────────────────────────────────────────────
|
|
print(f"Loading model: {args.model}", flush=True)
|
|
llama = Llama(
|
|
model_path=args.model,
|
|
n_ctx=4096,
|
|
n_gpu_layers=args.gpu_layers,
|
|
verbose=False,
|
|
)
|
|
|
|
# ── First inference ───────────────────────────────────────────
|
|
prompt1 = "The capital of France is"
|
|
print(f"\nPrompt 1: {prompt1!r}")
|
|
out1 = llama(prompt1, max_tokens=32, echo=False)
|
|
text1 = out1["choices"][0]["text"].strip()
|
|
print(f"Response: {text1}")
|
|
print(f"State size before save: {core.get_state_size(llama):,} bytes")
|
|
|
|
# ── Save state ────────────────────────────────────────────────
|
|
print(f"\nSaving state to {args.state} …")
|
|
core.save_state(llama, args.model, args.state)
|
|
saved_bytes = Path(args.state).stat().st_size
|
|
print(f"Saved ({saved_bytes:,} bytes on disk)")
|
|
|
|
# ── Second inference — accumulates on top of state 1 ─────────
|
|
prompt2 = " Its population is approximately"
|
|
print(f"\nPrompt 2 (continuous): {prompt2!r}")
|
|
out2 = llama(prompt2, max_tokens=24, echo=False)
|
|
text2 = out2["choices"][0]["text"].strip()
|
|
print(f"Response: {text2}")
|
|
|
|
# ── Reload the saved state ────────────────────────────────────
|
|
print(f"\nRestoring state from checkpoint …")
|
|
core.load_state(llama, args.model, args.state)
|
|
print("State restored.")
|
|
|
|
# ── Same prompt 2 again — should reproduce same answer ────────
|
|
print(f"\nPrompt 2 again (after restore): {prompt2!r}")
|
|
out3 = llama(prompt2, max_tokens=24, echo=False)
|
|
text3 = out3["choices"][0]["text"].strip()
|
|
print(f"Response: {text3}")
|
|
|
|
match = text2 == text3
|
|
print(f"\nReproducible? {'YES' if match else 'NO (expected for non-greedy sampling)'}")
|
|
print("\nDone.")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|