Instructions to use kurogane/Nemotron-H-micro-test03 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kurogane/Nemotron-H-micro-test03 with Transformers:

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

pipe = pipeline("text-generation", model="kurogane/Nemotron-H-micro-test03")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kurogane/Nemotron-H-micro-test03", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kurogane/Nemotron-H-micro-test03 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kurogane/Nemotron-H-micro-test03"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kurogane/Nemotron-H-micro-test03",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kurogane/Nemotron-H-micro-test03

SGLang

How to use kurogane/Nemotron-H-micro-test03 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 "kurogane/Nemotron-H-micro-test03" \
    --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": "kurogane/Nemotron-H-micro-test03",
		"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 "kurogane/Nemotron-H-micro-test03" \
        --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": "kurogane/Nemotron-H-micro-test03",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kurogane/Nemotron-H-micro-test03 with Docker Model Runner:
```
docker model run hf.co/kurogane/Nemotron-H-micro-test03
```

Configuration Parsing Warning:Invalid JSON for config file config.json

概要

NemotronHアーキテクチャのBaseモデルです。動作確認用に小規模データセットでトレーニングしたものです。 context sizeは512です。

dataset

hotchpotch/fineweb-2-edu-japaneseの1%のデータを含むデータセットで19 epochs回しました。

tokenizer

Rakuten/RakutenAI-2.0-mini-instructを使用しました。日本語対応LLMであり、vocab_sizeが48000と学習に使いやすそうだったからです。

sample code

chat templateは搭載していますが、全くチャット形式に対応していないので通常のテキスト生成飲みが可能です。

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "kurogane/Nemotron-H-micro-test03"
dir_cache = r"/media/kurogane/backup/cache"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True,
    cache_dir=dir_cache,
)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
    cache_dir=dir_cache,
)

inputs = tokenizer(
    "こんにちは", 
    return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs)
print(
    tokenizer.batch_decode(
        outputs, 
        skip_special_tokens=True,
    )
)

こんにちは！\n今回は、「教えて、お願い！」という方向けに、\n

Downloads last month: 9

Safetensors

Model size

0.4B params

Tensor type

BF16

Dataset used to train kurogane/Nemotron-H-micro-test03

Collection including kurogane/Nemotron-H-micro-test03

pretrained models

Collection

6 items • Updated Mar 15