Instructions to use geodesic-research/nemotron_120b_warm_start_sft_200k_instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use geodesic-research/nemotron_120b_warm_start_sft_200k_instruct with Transformers:

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

pipe = pipeline("text-generation", model="geodesic-research/nemotron_120b_warm_start_sft_200k_instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("geodesic-research/nemotron_120b_warm_start_sft_200k_instruct")
model = AutoModelForMultimodalLM.from_pretrained("geodesic-research/nemotron_120b_warm_start_sft_200k_instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use geodesic-research/nemotron_120b_warm_start_sft_200k_instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/geodesic-research/nemotron_120b_warm_start_sft_200k_instruct

SGLang

How to use geodesic-research/nemotron_120b_warm_start_sft_200k_instruct 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 "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct" \
    --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": "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct",
		"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 "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct" \
        --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": "geodesic-research/nemotron_120b_warm_start_sft_200k_instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use geodesic-research/nemotron_120b_warm_start_sft_200k_instruct with Docker Model Runner:
```
docker model run hf.co/geodesic-research/nemotron_120b_warm_start_sft_200k_instruct
```

Nemotron-3 120B-A12B — Warm-Start SFT 200k (instruct)

This is one of four canonical warm-start baselines for the Geodesic Research SFM / inoculation campaigns. Models trained with this checkpoint as the starting point should be directly comparable across the {30B, 120B} × {think, instruct} matrix.

Variant

instruct — uses the geodesic-research/nemotron-instruct-tokenizer, whose chat template never auto-injects <think>...</think> reasoning tags. Inference produces direct instruct-style responses without reasoning traces..

The encoder is byte-identical to the upstream nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 tokenizer; only the chat template differs from upstream.

Training data

HF dataset: geodesic-research/sft-warm-start-200k
Subset: no_think
Examples: 200,000 chat-format conversations (no held-out validation/test split)
Tokens: 259M (counted with the instruct tokenizer)
Sequence packing: pad_seq_to_mult=1, pad_to_max_length=false, packed sequence length 8192

Training recipe


Hardware	Isambard GH200, 16 nodes × 4 GPUs (sm_90, BF16)
Parallelism	TP=4, EP=4, PP=8, CP=1, ETP=1 (parallel folding)
Data parallelism	DP_pure=2, grad_accum=32
Global batch size	64 (× 8192 tokens = 524k tokens/batch)
Sequence length	8192
Optimizer	distributed Adam (β1=0.9, β2=0.95, ε=1e-8, wd=0.1, clip=1)
Learning rate	5e-06 (cosine decay to 0, 5% warmup)
Precision	BF16 + Precision-Aware Optimizer (BF16 momentum/variance) + activation offloading
Iterations	495 (≈ 1 epoch over the dataset)
W&B run	link

Downloads last month: 76

Safetensors

Model size

124B params

Tensor type

BF16

F32

Model tree for geodesic-research/nemotron_120b_warm_start_sft_200k_instruct

Base model

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

Finetuned

(17)

this model

Dataset used to train geodesic-research/nemotron_120b_warm_start_sft_200k_instruct

Collection including geodesic-research/nemotron_120b_warm_start_sft_200k_instruct

V2: Persona Inoculation <stage=training> Fyn1668

Collection

3 items • Updated Apr 28