Instructions to use SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16

SGLang

How to use SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16 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 "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16" \
    --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": "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16",
		"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 "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16" \
        --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": "SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16 with Docker Model Runner:
```
docker model run hf.co/SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16
```

Nemotron Super 49B AIE v11 5500 Merged BF16

This is a merged bf16 export of nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 with the local AIE v11 LoRA adapter merged into the base weights.

Training summary:

Dataset: aie_v11, 5,227 examples.
Stage 1: 4-bit LoRA SFT at cutoff_len=4096, 2 epochs.
Stage 2: continued from the stage 1 adapter at cutoff_len=5500, 2 epochs.
Stage 2 learning rate: 3e-5.
Stage 2 final train loss: 0.1407.
LoRA target modules: q_proj,v_proj.
Export dtype: bfloat16.

The merged model was exported with LLaMA-Factory and split into 21 safetensors shards.

Downloads last month: -

Safetensors

Model size

50B params

Tensor type

BF16

Model tree for SiddharthaChekuri/Nemotron-Super-49B-AIE-v11-5500-merged-bf16

Base model

nvidia/Llama-3_3-Nemotron-Super-49B-v1_5

Finetuned

(9)

this model