Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
rtferraz
/
tucano2-commerce
like
0
Model card
Files
Files and versions
xet
Community
main
tucano2-commerce
/
notebooks
Ctrl+K
Ctrl+K
2 contributors
History:
21 commits
rtferraz
add: base vs tuned comparison cell for V4.2 final evaluation
0c9199c
verified
5 days ago
cell_comparison_base_vs_tuned.py
Safe
16.3 kB
add: base vs tuned comparison cell for V4.2 final evaluation
5 days ago
grpo_vertex_v3.ipynb
Safe
82.6 kB
apply v3 task-aware thinking controls and delete deprecated notebook
14 days ago
v4_1_instruct_grpo.ipynb
Safe
50.3 kB
notebooks: add V4.1 GRPO notebook (parser fix, 600 steps, LR 5e-6, constant_with_warmup)
10 days ago
v4_2_instruct_grpo.ipynb
Safe
90.8 kB
feat(rewards): add sentiment mismatch penalty to prevent extraction reward hacking
6 days ago
v4_instruct_grpo.ipynb
Safe
47.7 kB
v4: ROOT CAUSE FIX — use standard PEFT not Unsloth get_peft_model (fused LoRA kernels have dtype bug #4891). Revert to load_in_4bit=True, dtype=None matching V3.
12 days ago
