Instructions to use helenai/ibm-granite-granite-8b-code-instruct-ov with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use helenai/ibm-granite-granite-8b-code-instruct-ov with Transformers:

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

pipe = pipeline("text-generation", model="helenai/ibm-granite-granite-8b-code-instruct-ov")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("helenai/ibm-granite-granite-8b-code-instruct-ov")
model = AutoModelForCausalLM.from_pretrained("helenai/ibm-granite-granite-8b-code-instruct-ov")
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

vLLM

How to use helenai/ibm-granite-granite-8b-code-instruct-ov with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "helenai/ibm-granite-granite-8b-code-instruct-ov"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "helenai/ibm-granite-granite-8b-code-instruct-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/helenai/ibm-granite-granite-8b-code-instruct-ov

SGLang

How to use helenai/ibm-granite-granite-8b-code-instruct-ov 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 "helenai/ibm-granite-granite-8b-code-instruct-ov" \
    --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": "helenai/ibm-granite-granite-8b-code-instruct-ov",
		"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 "helenai/ibm-granite-granite-8b-code-instruct-ov" \
        --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": "helenai/ibm-granite-granite-8b-code-instruct-ov",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use helenai/ibm-granite-granite-8b-code-instruct-ov with Docker Model Runner:
```
docker model run hf.co/helenai/ibm-granite-granite-8b-code-instruct-ov
```

ibm-granite/granite-8b-code-instruct

This is the ibm-granite/granite-8b-code-instruct model converted to OpenVINO with INT8 weights compression for accelerated inference.

An example of how to do inference on this model:

# pip install optimum[openvino]
from transformers import AutoTokenizer
from optimum.intel import OVModelForCausalLM

model_path = "helenai/ibm-granite-granite-8b-code-instruct-ov"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = OVModelForCausalLM.from_pretrained(model_path)

# change input text as desired
chat = [
    { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
# tokenize the text
input_tokens = tokenizer(chat, return_tensors="pt")
# generate output tokens
output = model.generate(**input_tokens, max_new_tokens=100)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# loop over the batch to print, in this example the batch size is 1
for i in output:
    print(i)

Downloads last month: 3