Downloads · 30 days
0
W-61/b200-l3-ultra-sel-dpo-b0p01-s1001-v1-a2
b200-l3-ultra-sel-dpo-b0p01-s1001-v1-a2 is a machine learning model from W-61. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
Downloads · 30 days
0
Access
Public
Updated Jul 27, 2026
Repo size
161 GB
Likes
0
Public
Click a slice to open those files.
.safetensors161 GB · 100%
From the Hugging Face model README
Built with Meta Llama 3.
This public repository is a curated evaluation handoff for one approved Phase 3 candidate. It contains only loadable Transformers-format exports for retained steps 300, 400, and 477. Native FSDP optimizer/restart state, raw evaluation outputs, logs, credentials, and private evidence are intentionally excluded.
Load an exact retained checkpoint by choosing one of:
checkpoint-300checkpoint-400checkpoint-477The root PROVENANCE.json records byte sizes, SHA-256 digests, the preserved
fresh-load validation shapes, and the source recovery evidence hashes. The
original attempt status is not rewritten by this derived public export.