Downloads · 30 days
14
10% of all-time downloads
tzchen07/rai-nemotron3-nano-dpo-w2c
rai-nemotron3-nano-dpo-w2c is a machine learning model from tzchen07. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Nemotron-3-Nano-4B → v3dtjpi3o6 (full-SFT) → DPO. lowest v14, most recall cost.
Downloads · 30 days
14
10% of all-time downloads
All-time downloads
143
Public
Parameters
4B
8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.9 GB · 100%
From the Hugging Face model README
Nemotron-3-Nano-4B → v3d_tjpi3o6 (full-SFT) → DPO. lowest v14, most recall cost.
DPO (β0.05, LoRA r32) from v3d_tjpi3o6 on combined v1+wave2 (1250) — preference pairs that fix confident benign
false-blocks (JB own-agent-control §07, IP own-content §08, PII synthetic §09, feedback-reading §13)
with contrastive recall-preserve pairs. DPO's non-saturating gradient moved the confident-cluster
false-blocks that full-SFT (100+ arms) walled at 0.36%.
| v14 Block% | hello R | v200-P | v200-R | rvR | rvP |
|---|---|---|---|---|---|
| 0.2% | 0.707 | 0.996 | 0.865 | 0.86 | 0.933 |
vs the tjpi3o6 base (v14 0.36 / rvP 0.914 / v200-P 0.990): v14 down, precision up (rvP, v200-P), recall held — DPO reduced benign false-blocks, which lifts every precision metric at once.
vllm serve <repo> --trust-remote-code --mamba_ssm_cache_dtype float32