Instructions to use optimum-intel-internal-testing/tiny-random-nemotron-h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use optimum-intel-internal-testing/tiny-random-nemotron-h with Transformers:

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

pipe = pipeline("text-generation", model="optimum-intel-internal-testing/tiny-random-nemotron-h")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("optimum-intel-internal-testing/tiny-random-nemotron-h")
model = AutoModelForCausalLM.from_pretrained("optimum-intel-internal-testing/tiny-random-nemotron-h", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use optimum-intel-internal-testing/tiny-random-nemotron-h with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/optimum-intel-internal-testing/tiny-random-nemotron-h

SGLang

How to use optimum-intel-internal-testing/tiny-random-nemotron-h 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 "optimum-intel-internal-testing/tiny-random-nemotron-h" \
    --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": "optimum-intel-internal-testing/tiny-random-nemotron-h",
		"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 "optimum-intel-internal-testing/tiny-random-nemotron-h" \
        --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": "optimum-intel-internal-testing/tiny-random-nemotron-h",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use optimum-intel-internal-testing/tiny-random-nemotron-h with Docker Model Runner:
```
docker model run hf.co/optimum-intel-internal-testing/tiny-random-nemotron-h
```

Rename backbone.embedding.weight to backbone.embeddings.weight

by alejandro-rodriguez - opened about 11 hours ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-1

alejandro-rodriguez

about 11 hours ago

Hugging Face CLI

transformers 5.15 saved the NemotronH embeddings as backbone.embedding.weight, and this model was saved with it. NVIDIA checkpoints use backbone.embeddings.weight, and transformers 5.16 dropped the rule that mapped the singular key (https://github.com/huggingface/transformers/pull/48075), so from 5.16 the model loads with random embeddings.

This only renames the key and adds a line about it to the README (same files as https://huggingface.co/alejandro-rodriguez/tiny-random-nemotron-h/commit/f93d1078a6eb69169db59de24113bb3851b88f2f). With transformers 5.15.1 and 5.22.2 it loads the same weights that 5.15.1 loaded before.

Rename backbone.embedding.weight to backbone.embeddings.weight5b1d8910

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment