vh
475d6d6bcb
Operator ask relayed by brokkr-smithy-dev. Positive control (SemIf 187/231, hard 0.613) reproduced exactly; negative control and a 4-restart noise floor (0 flips) measured. On our replaced-baseline sets no candidate beats SemIf-with- rotations beyond the ~4-pt floor; Intern-Decision-4B native matches it at one ordering, is better on Wyrd, fits 9.7/10.3 GB and is 1.5-2.3x faster. JevBench rank does not transfer. Raw per-item data kept out of git.
15 lines
691 B
Python
15 lines
691 B
Python
import os, sys, time
|
|
from huggingface_hub import snapshot_download
|
|
PINS = [
|
|
("crh225/plumb-4b", "55de037801a8a9b9de3db5c0e16cef86210c2186", None),
|
|
("alibiserikbay/JevK5", "27d2d6b8d4714807f6293b0623bd7370b27e42f8", None),
|
|
("internlm/Intern-Decision-4B", "0e5e6aa7d6d750e2b1504ba11a8136cb58aeb3cd", None),
|
|
("mohit67890/imajev-4b", "c9e5f132465da85d31735ec502d5557982671a7d", ["mlx/*", "assets/*"]),
|
|
]
|
|
only = sys.argv[1:] or [p[0] for p in PINS]
|
|
for repo, rev, ignore in PINS:
|
|
if repo not in only: continue
|
|
t = time.time()
|
|
path = snapshot_download(repo, revision=rev, ignore_patterns=ignore)
|
|
print(f"{repo}@{rev} -> {path} in {time.time()-t:.0f}s", flush=True)
|