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

Libraries

How to use ibm-granite/granite-8b-code-base-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-base-4k")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-8b-code-base-4k")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-8b-code-base-4k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ibm-granite/granite-8b-code-base-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-base-4k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-8b-code-base-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use ibm-granite/granite-8b-code-base-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-base-4k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-8b-code-base-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-base-4k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-8b-code-base-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

amezasor commited on May 4, 2024

Commit

ea2cd2d

verified ·

1 Parent(s): 9e5f74e

model summary update

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -251,7 +251,7 @@ model-index:
 # Granite-8B-Code-Base
 ## Model Summary
-**Granite-8B-Code-Base** is a decoder-only code model designed for code generative tasks (e.g., code generation, code explanation, code fixing, etc.). It is trained from scratch with a two-phase training strategy. In phase 1, our model is trained on 3 to 4 trillion tokens sourced from 116 programming languages, ensuring a comprehensive understanding of programming languages and syntax. In phase 2, our model is trained on 500 billion tokens with a carefully designed mixture of high-quality data from code and natural language domains to improve the models’ ability to reason and follow instructions.
 - **Developers:** IBM Research
 - **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)

 # Granite-8B-Code-Base
 ## Model Summary
+**Granite-8B-Code-Base** is a decoder-only code model designed for code generative tasks (e.g., code generation, code explanation, code fixing, etc.). It is trained from scratch with a two-phase training strategy. In phase 1, our model is trained on 4 trillion tokens sourced from 116 programming languages, ensuring a comprehensive understanding of programming languages and syntax. In phase 2, our model is trained on 500 billion tokens with a carefully designed mixture of high-quality data from code and natural language domains to improve the models’ ability to reason and follow instructions.
 - **Developers:** IBM Research
 - **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)