Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

rtferraz
/
tucano2-commerce

Model card Files Files and versions
xet
Community
tucano2-commerce
354 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 22 commits
rtferraz's picture
rtferraz
v4: fix NF4 fp16/bf16 dtype bug (unsloth #4891) β€” load_in_4bit=False, 0.5B fits in full bf16 on 24GB
ca397a5 verified 13 days ago
  • docs
    ADR-002: V4 Instruct-Only GRPO β€” revises dual-model plan based on model repo audit 13 days ago
  • notebooks
    v4: fix NF4 fp16/bf16 dtype bug (unsloth #4891) β€” load_in_4bit=False, 0.5B fits in full bf16 on 24GB 13 days ago
  • scripts
    tools: add md-to-ipynb converter script 15 days ago
  • .gitattributes
    1.52 kB
    initial commit 15 days ago
  • .gitignore
    497 Bytes
    Initial commit: Tucano2-Commerce GRPO v3 training pipeline 15 days ago
  • grpo_vertex_v2_ipynb.md
    58.3 kB
    Create grpo_vertex_v2_ipynb.md 15 days ago