Instructions to use ibm-granite/granite-8b-code-instruct-4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-8b-code-instruct-4k with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-8b-code-instruct-4k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-8b-code-instruct-4k")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-8b-code-instruct-4k")
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 ibm-granite/granite-8b-code-instruct-4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-8b-code-instruct-4k"
# 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-8b-code-instruct-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-8b-code-instruct-4k

SGLang

How to use ibm-granite/granite-8b-code-instruct-4k 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-8b-code-instruct-4k" \
    --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-8b-code-instruct-4k",
		"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-8b-code-instruct-4k" \
        --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-8b-code-instruct-4k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibm-granite/granite-8b-code-instruct-4k with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-8b-code-instruct-4k
```

Function calling and Streaming support

by skumarai - opened Jun 4, 2024

Discussion

skumarai

Jun 4, 2024

Hi ,
I've been exploring the IBM Granite models and have a couple of questions that I'd appreciate if someone could help me with.

Function Calling: I haven't found any documentation or resources that indicate whether IBM Granite models support function calling, i.e., invoking a particular function or method of the model. Can anyone confirm if this feature is supported?

Streaming: Similarly, I'm also curious to know whether IBM Granite models support Streaming. any pointers or resources in this regard would be greatly appreciated.

I've searched through both the Git repo and Hugging Face documentation but haven't found clear information on these features. If anyone has any insights, it would be a great help.

Thanks.

skumarai

Jun 24, 2024

Hi @mayank-mishra

Any help you could provide in above ?
Thanks.

mayank-mishra

Jun 25, 2024

@skumarai function calling might work with the model but its not an actively trained feature AFAIK.
I think HuggingFace doesn't support streaming.
And streaming has nothing to do with the model but rather the HuggingFace ecosystem.
I suggest you take a look at vllm: https://github.com/vllm-project/vllm

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