wassname/evil_MoE
1
0
Fork 0
mirror of https://github.com/wassname/evil_MoE.git synced 2026-08-11 11:18:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

rename python package projected_grpo -> vgrout

Browse Source 
git mv src/projected_grpo -> src/vgrout and find-replace the module name in
all imports (.py), `-m projected_grpo.*` invocations (justfile), and the
[project] name (pyproject; setuptools auto-discovers via where=["src"]).

Left RESEARCH_JOURNAL.md untouched: its commands/paths are dated lab notes
tied to past commits, so rewriting them would falsify provenance. Repo dir,
git remote, and absolute paths unchanged.

Verified: `import vgrout` and `python -m vgrout.train --help` load the full
graph; verify_rewards.py + verify_gate_anchor.py (both import vgrout) pass.
Full `just smoke` is blocked upstream by missing gitignored data artifacts
(out/pools/{substrate,teacher_pool}, out/vhack/*smoke*), unrelated to the rename.
This commit is contained in:
wassname
2026-06-05 14:51:48 +08:00
parent 03693e4f30
commit 55937a86fb
32 changed files with 65 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/probe_distill.py
+6 -6
View File
@@ -51,12 +51,12 @@ from loguru import logger
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from projected_grpo.antipasto import wrap_model_with_antipasto
from projected_grpo.proj import per_token_logps, project_delta_S_grad
from projected_grpo.rewards import compute_reward
from projected_grpo.train import CACHE_ROOT, OUT_DIR, setup_logging
from projected_grpo.problems import DATA, load_problems
from projected_grpo.extract_vhack_grad import load_v_hack
from vgrout.antipasto import wrap_model_with_antipasto
from vgrout.proj import per_token_logps, project_delta_S_grad
from vgrout.rewards import compute_reward
from vgrout.train import CACHE_ROOT, OUT_DIR, setup_logging
from vgrout.problems import DATA, load_problems
from vgrout.extract_vhack_grad import load_v_hack
STUDENT_MODEL = "Qwen/Qwen3-4B"