Instructions to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("nvidia/Llama-3_3-Nemotron-Super-49B-v1_5")
model = PeftModel.from_pretrained(base_model, "SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k")

Transformers

How to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k with Transformers:

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

pipe = pipeline("text-generation", model="SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k"
# 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-49b-aie-v11-lora-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k

SGLang

How to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k 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-49b-aie-v11-lora-4k" \
    --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-49b-aie-v11-lora-4k",
		"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-49b-aie-v11-lora-4k" \
        --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-49b-aie-v11-lora-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k with Docker Model Runner:
```
docker model run hf.co/SiddharthaChekuri/nemotron-49b-aie-v11-lora-4k
```

nemotron-49b-aie-v11-lora-4k / README.md

SiddharthaChekuri

Upload Nemotron 49B AIE v11 4k LoRA adapter

03b879c verified 4 months ago

preview code

Raw History Blame Contribute Delete

1.56 kB

	---
	library_name: peft
	license: other
	base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
	tags:
	- base_model:adapter:nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
	- llama-factory
	- lora
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: aie_v11_4096_4bit_working_20260606_101923
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# aie_v11_4096_4bit_working_20260606_101923

	This model is a fine-tuned version of [nvidia/Llama-3_3-Nemotron-Super-49B-v1_5](https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5) on the aie_v11 dataset.

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 5e-05
	- train_batch_size: 1
	- eval_batch_size: 8
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 2
	- gradient_accumulation_steps: 32
	- total_train_batch_size: 64
	- total_eval_batch_size: 16
	- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_ratio: 0.03
	- num_epochs: 2.0

	### Training results



	### Framework versions

	- PEFT 0.18.1
	- Transformers 4.52.4
	- Pytorch 2.10.0+cu128
	- Datasets 4.0.0
	- Tokenizers 0.21.4