mirror of
https://github.com/wassname/evil_MoE.git
synced 2026-09-11 14:52:47 +08:00
cleanup: consolidate stale loaders and pair scripts
This commit is contained in:
@@ -28,8 +28,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
from vgrout.antipasto import wrap_model_with_antipasto
|
||||
from vgrout.extract_vhack_grad import completion_nll, resolve_dtype
|
||||
from vgrout.pairs import PAIRS
|
||||
from vgrout.extract_vhack_grad import load_v_hack
|
||||
from vgrout.pairs_from_pool import load_pairs_json
|
||||
from vgrout.vhack import load_v_hack
|
||||
|
||||
|
||||
CACHE_ROOT = Path("svd_cache")
|
||||
@@ -42,6 +42,7 @@ class Config:
|
||||
dtype: str = "bf16" # must match extract_vhack_grad.py and train.py
|
||||
v_hack_path: Path = OUT_DIR / "vhack" / "v_hack_rh25.safetensors"
|
||||
out_path: Path = OUT_DIR / "vhack_heldout_cos_rh25.safetensors"
|
||||
pairs_path: Path = OUT_DIR / "pairsets" / "prog_wide.json"
|
||||
n_heldout: int = 2
|
||||
|
||||
|
||||
@@ -50,8 +51,9 @@ def main(cfg: Config) -> int:
|
||||
dtype = resolve_dtype(cfg.dtype)
|
||||
logger.info(f"device={device} model={cfg.model} dtype={cfg.dtype}")
|
||||
|
||||
held = PAIRS[-cfg.n_heldout:]
|
||||
logger.info(f"held-out pairs: {len(held)}")
|
||||
pairs = load_pairs_json(cfg.pairs_path)
|
||||
held = pairs[-cfg.n_heldout:]
|
||||
logger.info(f"held-out pairs: {len(held)} from {cfg.pairs_path}")
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(cfg.model)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
|
||||
Reference in New Issue
Block a user