Instructions to use ibm-granite/granite-3.0-2b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-3.0-2b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-3.0-2b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-3.0-2b-instruct")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-3.0-2b-instruct", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ibm-granite/granite-3.0-2b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-3.0-2b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-3.0-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-3.0-2b-instruct

SGLang

How to use ibm-granite/granite-3.0-2b-instruct 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 "ibm-granite/granite-3.0-2b-instruct" \
    --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": "ibm-granite/granite-3.0-2b-instruct",
		"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 "ibm-granite/granite-3.0-2b-instruct" \
        --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": "ibm-granite/granite-3.0-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibm-granite/granite-3.0-2b-instruct with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-3.0-2b-instruct
```

Model response concatenated

by inuwamobarak - opened Oct 25, 2024

Discussion

inuwamobarak

Oct 25, 2024

Why is the response concatenated like this:

# Define the input prompt
chat = [
    { 
        "role": "user", 
        "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." 
    },
]

# Tokenize input
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(chat, return_tensors="pt").to(device)

# Generate model output
output = model.generate(**input_tokens, max_new_tokens=100)

# Decode and print the response
response = tokenizer.batch_decode(output, skip_special_tokens=True)
print(response)

RESPONSE:
userPlease list one IBM Research laboratory located in the United States. You should only output its name and location.
assistant1. IBM Research - Austin, Texas

Why is there no space between the user or assistant and the string?

gabegoodhart

IBM Granite org Dec 10, 2024

Hi @inuwamobarak , thanks for your interest in this model! You've provided the skip_special_tokens=True flag to batch_decode which removes the special tokens that would normally separate the role and content fields in the model response. If you set that to False, it should insert the special separator tokens.

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("granite-3.0-2b-instruct")
model = AutoModelForCausalLM.from_pretrained("granite-3.0-2b-instruct")

chat = [
    { 
        "role": "user", 
        "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." 
    },
]

chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
input_tokens = tokenizer(chat, return_tensors="pt")
output = model.generate(**input_tokens, max_new_tokens=100)

print(tokenizer.batch_decode(output, skip_special_tokens=True))
# Output: ['userPlease list one IBM Research laboratory located in the United States. You should only output its name and location.\nassistant1. IBM Research - Austin, Texas']

print(tokenizer.batch_decode(output, skip_special_tokens=False))
# Output: ['<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>1. IBM Research - Austin, Texas<|end_of_text|>']

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

Tap or paste here to upload images

· Sign up or log in to comment