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

Libraries

How to use ticlazau/granite-8b-instruct-rpgle with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ticlazau/granite-8b-instruct-rpgle")
model = AutoModelForCausalLM.from_pretrained("ticlazau/granite-8b-instruct-rpgle")
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 ticlazau/granite-8b-instruct-rpgle with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ticlazau/granite-8b-instruct-rpgle

SGLang

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

Docker Model Runner
How to use ticlazau/granite-8b-instruct-rpgle with Docker Model Runner:
```
docker model run hf.co/ticlazau/granite-8b-instruct-rpgle
```

EXPERIMENTAL LLM for RPG based on Granite-8b-instruct

Summary:

This is an experimental LLM for RPG Programming in ILE that covers:

translation (ILE RPG code from fixed-form to free-form)
summarisation (ILE RPG code to text)
prototyping (text to ILE RPG code)

Dataset

Private dataset created via SDG

Additional info for RPG Programming in ILE :

https://www.ibm.com/docs/en/i/7.5?topic=introduction-rpg-programming-in-ile

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F16