Downloads · 30 days
3
5% of all-time downloads
tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001
Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 is a text generation model from tzchen07. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Full-parameter SFT of NVIDIA Nemotron-3-Super-120B (hybrid Mamba-2 + Latent-MoE, top-22 routing over 512 experts) for the Rovo Chat long-horizon (LH) orchestrator task: given a multi-turn conversation + a tool catalog…
Downloads · 30 days
3
5% of all-time downloads
All-time downloads
66
Public
Parameters
124B
241 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors241 GB · 100%
How the weights are stored.
BF16121B · 100%
From the Hugging Face model README
Full-parameter SFT of NVIDIA Nemotron-3-Super-120B (hybrid Mamba-2 + Latent-MoE, top-22 routing over 512 experts) for the Rovo Chat long-horizon (LH) orchestrator task: given a multi-turn conversation + a tool catalog, decide whether to answer in text or call the right tool with the right arguments.
| model | overall | text | tool |
|---|---|---|---|
| This SFT (iter_001) | 70.5% | 78.9% | 46.8% |
| base Nemotron-3-Super-120B (think_off) | 68.0% | 77.2% | 42.1% |
| Qwen3-32B | 71.0% | 85.4% | 30.5% |
| Gemma-4-31B | 84.8% | 95.9% | 53.7% |
Beats the base model on all three metrics (+2.5 overall, +1.7 text, +4.7 tool). The largest gain is on tool-calling — the base's weakest dimension — and this model's tool accuracy also exceeds Qwen3-32B's.
capacity_factor=1.5, full activation recompute, CPU-offloaded distributed optimizer.The 124.5B top-22/512-expert MoE + the ~11K-token Rovo system prompt cap full-parameter training to seq=16384 on 4×H200, so each example was right-anchored-truncated to system + a few tools + recent context + the final assistant turn — the full ~46K-median agentic traces do not fit. The model still improved over base; remaining errors (spurious/missed/wrong tool) should shrink with the full-length context that a larger GPU budget would unlock.
Fine-tuned on internal Atlassian Rovo production data.