Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
k0r1st
/
sair-modmul-entry1
like
0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
sair-modmul-entry1
79.5 MB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
k0r1st
Entry1 v3-B (tier-5 free-option): attempt all context-fitting tiers; timeout rule protects completed tiers. Local tier90=5 overall=0.498 det; T5 decode 263s may exceed official 300s budget -> degrades to tier4
7925822
verified
28 days ago
.gitattributes
Safe
1.52 kB
initial commit
28 days ago
manifest.json
Safe
3.02 kB
Entry1 v3-A (guaranteed floor): v3 trace model (T3/T4 100%), tier-0 diagnostic abstention, representative-depth attempt benchmark; tier90=4 overall=0.40 local, 65s/300s
28 days ago
model.py
Safe
10.8 kB
Entry1 v3-B (tier-5 free-option): attempt all context-fitting tiers; timeout rule protects completed tiers. Local tier90=5 overall=0.498 det; T5 decode 263s may exceed official 300s budget -> degrades to tier4
28 days ago
model_trace.py
Safe
14.4 kB
Entry1 v3-A (guaranteed floor): v3 trace model (T3/T4 100%), tier-0 diagnostic abstention, representative-depth attempt benchmark; tier90=4 overall=0.40 local, 65s/300s
28 days ago
trace_runtime.py
Safe
3.92 kB
Entry1 v3-A (guaranteed floor): v3 trace model (T3/T4 100%), tier-0 diagnostic abstention, representative-depth attempt benchmark; tier90=4 overall=0.40 local, 65s/300s
28 days ago
weights_small.pt
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
22.4 MB
xet
Entry1 v1: T1-T2 full-coverage head + T3-T5 trace transformer (ckpt_prod3 step 316k)
28 days ago
weights_trace.pt
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"model_trace.ModelConfig"
How to fix it?
57.1 MB
xet
Entry1 v3-A (guaranteed floor): v3 trace model (T3/T4 100%), tier-0 diagnostic abstention, representative-depth attempt benchmark; tier90=4 overall=0.40 local, 65s/300s
28 days ago