Instructions to use tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001

SGLang

How to use tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001 with Docker Model Runner:
```
docker model run hf.co/tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001
```

Configuration Parsing Warning:Invalid JSON for config file config.json

Nemotron-3-Super-120B — Rovo Chat Orchestrator SFT (iter_001)

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.

Results — 725-example LH-orchestrator answer-accuracy (Claude-Opus-4.8 judge)

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.

Training

Stack: Megatron-Core 0.16.1 + Megatron-Bridge (full-parameter SFT, not LoRA).
Recipe: 1 epoch (366 steps, ~~2.1 h), LR 2e-6 cosine (~~5% warmup), weight_decay 0.1, GBS 16, bf16; train loss 1.47→1.20 (stable).
Parallelism / memory: TP=8 / EP=8 / DP=4 on 4×H200; FlashAttention 2.8.3, MoE expert capacity_factor=1.5, full activation recompute, CPU-offloaded distributed optimizer.
Data: Rovo Chat Orchestrator SFT v3 (high-quality prod traces, CSR>90), 5,849 examples after prep.

Known limitation (next-iteration target)

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.

Downloads last month: 21

Safetensors

Model size

124B params

Tensor type

F32

BF16

Model tree for tzchen07/Nemotron-3-Super-120B-rovochat-orchestrator-sft-iter001

Base model

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Finetuned

(19)

this model