Instructions to use mgoin/Nemotron-4-340B-Base-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mgoin/Nemotron-4-340B-Base-hf with Transformers:

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

pipe = pipeline("text-generation", model="mgoin/Nemotron-4-340B-Base-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mgoin/Nemotron-4-340B-Base-hf")
model = AutoModelForCausalLM.from_pretrained("mgoin/Nemotron-4-340B-Base-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mgoin/Nemotron-4-340B-Base-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mgoin/Nemotron-4-340B-Base-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgoin/Nemotron-4-340B-Base-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mgoin/Nemotron-4-340B-Base-hf

SGLang

How to use mgoin/Nemotron-4-340B-Base-hf 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 "mgoin/Nemotron-4-340B-Base-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgoin/Nemotron-4-340B-Base-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "mgoin/Nemotron-4-340B-Base-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mgoin/Nemotron-4-340B-Base-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mgoin/Nemotron-4-340B-Base-hf with Docker Model Runner:
```
docker model run hf.co/mgoin/Nemotron-4-340B-Base-hf
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Nemotron-4-340B-Base-hf

Converted checkpoint of nvidia/Nemotron-4-340B-Base. Specifically it was produced from the v1.2 .nemo checkpoint on NGC.

You can deploy this model with vllm>=0.5.4 (PR#6611):

vllm serve mgoin/Nemotron-4-340B-Base-hf --tensor-parallel-size 16

Evaluations

All the below evaluations were run with the FP8 checkpoint using lm-eval==0.4.3 on 8xA100 GPUs.

lm_eval --model vllm --model_args pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend="ray",max_model_len=4096,gpu_memory_utilization=0.6 --tasks truthfulqa_mc2 --num_fewshot 0 --batch_size 16
vllm (pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend=ray,max_model_len=4096,gpu_memory_utilization=0.6), gen_kwargs: (None), limit: None, num_fewshot: 0, batch_size: 16
|    Tasks     |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|--------------|------:|------|-----:|------|---|-----:|---|-----:|
|truthfulqa_mc2|      2|none  |     0|acc   |↑  |0.4869|±  |0.0142|

lm_eval --model vllm --model_args pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend="ray",max_model_len=4096,gpu_memory_utilization=0.6 --tasks winogrande --num_fewshot 5 --batch_size 16
vllm (pretrained=/home/mgoin/code/Nemotron-4-340B-Base-hf-FP8,tensor_parallel_size=8,distributed_executor_backend=ray,max_model_len=4096,gpu_memory_utilization=0.6), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
|  Tasks   |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|----------|------:|------|-----:|------|---|-----:|---|-----:|
|winogrande|      1|none  |     5|acc   |↑  |0.8887|±  |0.0088|

The original paper evals for reference: