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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NitroLLM/granite-8b-code-instruct-4k-openvino"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NitroLLM/granite-8b-code-instruct-4k-openvino",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

NitroLLM commited on Feb 17, 2025

Commit

0d2015c

verified ·

1 Parent(s): 459ed94

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +104 -0

README.md ADDED Viewed

	@@ -0,0 +1,104 @@

+---
+pipeline_tag: text-generation
+base_model: ibm-granite/granite-8b-code-instruct-4k
+inference: false
+license: apache-2.0
+datasets:
+- bigcode/commitpackft
+- TIGER-Lab/MathInstruct
+- meta-math/MetaMathQA
+- glaiveai/glaive-code-assistant-v3
+- glaive-function-calling-v2
+- bugdaryan/sql-create-context-instruction
+- garage-bAInd/Open-Platypus
+- nvidia/HelpSteer
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+- openvino
+- openvino-export
+model-index:
+- name: granite-8b-code-instruct-4k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis(Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 57.9
+      name: pass@1
+    - type: pass@1
+      value: 52.4
+      name: pass@1
+    - type: pass@1
+      value: 58.5
+      name: pass@1
+    - type: pass@1
+      value: 43.3
+      name: pass@1
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 37.2
+      name: pass@1
+    - type: pass@1
+      value: 53.0
+      name: pass@1
+    - type: pass@1
+      value: 42.7
+      name: pass@1
+    - type: pass@1
+      value: 52.4
+      name: pass@1
+    - type: pass@1
+      value: 36.6
+      name: pass@1
+    - type: pass@1
+      value: 43.9
+      name: pass@1
+    - type: pass@1
+      value: 16.5
+      name: pass@1
+    - type: pass@1
+      value: 39.6
+      name: pass@1
+    - type: pass@1
+      value: 40.9
+      name: pass@1
+    - type: pass@1
+      value: 48.2
+      name: pass@1
+    - type: pass@1
+      value: 41.5
+      name: pass@1
+    - type: pass@1
+      value: 39.0
+      name: pass@1
+    - type: pass@1
+      value: 32.9
+      name: pass@1
+---
+This model was converted to OpenVINO from [`ibm-granite/granite-8b-code-instruct-4k`](https://huggingface.co/ibm-granite/granite-8b-code-instruct-4k) using [optimum-intel](https://github.com/huggingface/optimum-intel)
+via the [export](https://huggingface.co/spaces/echarlaix/openvino-export) space.
+First make sure you have optimum-intel installed:
+```bash
+pip install optimum[openvino]
+```
+To load your model you can do as follows:
+```python
+from optimum.intel import OVModelForCausalLM
+model_id = "NitroLLM/granite-8b-code-instruct-4k-openvino"
+model = OVModelForCausalLM.from_pretrained(model_id)
+```