Instructions to use unsloth/grok-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/grok-2 with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/grok-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("unsloth/grok-2")
model = AutoModelForCausalLM.from_pretrained("unsloth/grok-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/grok-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/grok-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/grok-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/grok-2

SGLang

How to use unsloth/grok-2 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 "unsloth/grok-2" \
    --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": "unsloth/grok-2",
		"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 "unsloth/grok-2" \
        --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": "unsloth/grok-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use unsloth/grok-2 with Docker Model Runner:
```
docker model run hf.co/unsloth/grok-2
```

Grok-2 Tokenizer

A 🤗-compatible version of the Grok-2 tokenizer (adapted from xai-org/grok-2).

This means it can be used with Hugging Face libraries including Transformers, Tokenizers, and Transformers.js.

Motivation

As Grok 2.5 aka. xai-org/grok-2 has been recently released on the 🤗 Hub with SGLang native support, but the checkpoints on the Hub won't come with a Hugging Face compatible tokenizer, but rather with a tiktoken-based JSON export, which is internally read and patched in SGLang.

This repository then contains the Hugging Face compatible export so that users can easily interact and play around with the Grok-2 tokenizer, besides that allowing to use it via SGLang without having to pull the repository manually from the Hub and then using a mount, to prevent from directly having to point to the tokenizer path, so that Grok-2 can be deployed as:

python3 -m sglang.launch_server --model-path xai-org/grok-2 --tokenizer-path alvarobartt/grok-2-tokenizer --tp-size 8 --quantization fp8 --attention-backend triton

Rather than the former 2-step process:

hf download xai-org/grok-2 --local-dir /local/grok-2

python3 -m sglang.launch_server --model-path /local/grok-2 --tokenizer-path /local/grok-2/tokenizer.tok.json --tp-size 8 --quantization fp8 --attention-backend triton

Example

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("alvarobartt/grok-2-tokenizer")

assert tokenizer.encode("Human: What is Deep Learning?<|separator|>\n\n") == [
    35406,
    186,
    2171,
    458,
    17454,
    14803,
    191,
    1,
    417,
]

assert (
    tokenizer.apply_chat_template(
        [{"role": "user", "content": "What is the capital of France?"}], tokenize=False
    )
    == "Human: What is the capital of France?<|separator|>\n\n"
)

This repository has been inspired by earlier similar work by Xenova in Xenova/grok-1-tokenizer.

Downloads last month: 86