Instructions to use TevunahAi/granite-20b-code-instruct-8k-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TevunahAi/granite-20b-code-instruct-8k-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="TevunahAi/granite-20b-code-instruct-8k-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TevunahAi/granite-20b-code-instruct-8k-FP8")
model = AutoModelForCausalLM.from_pretrained("TevunahAi/granite-20b-code-instruct-8k-FP8", 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 TevunahAi/granite-20b-code-instruct-8k-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TevunahAi/granite-20b-code-instruct-8k-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TevunahAi/granite-20b-code-instruct-8k-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TevunahAi/granite-20b-code-instruct-8k-FP8

SGLang

How to use TevunahAi/granite-20b-code-instruct-8k-FP8 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 "TevunahAi/granite-20b-code-instruct-8k-FP8" \
    --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": "TevunahAi/granite-20b-code-instruct-8k-FP8",
		"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 "TevunahAi/granite-20b-code-instruct-8k-FP8" \
        --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": "TevunahAi/granite-20b-code-instruct-8k-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TevunahAi/granite-20b-code-instruct-8k-FP8 with Docker Model Runner:
```
docker model run hf.co/TevunahAi/granite-20b-code-instruct-8k-FP8
```

rockylynnstein commited on Dec 8, 2025

Commit

aec9cca

verified ·

1 Parent(s): 22f2164

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -6

README.md CHANGED Viewed

@@ -52,13 +52,16 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```python
 from vllm import LLM, SamplingParams
-llm = LLM(model="TevunahAi/granite-20b-code-instruct-8k-FP8")
-sampling_params = SamplingParams(temperature=0.7, max_tokens=256)
-prompts = ["Write a Python function to calculate fibonacci numbers:"]
-outputs = llm.generate(prompts, sampling_params)
 ```
 ## Quantization Details
 - **Target Layers:** All Linear layers except lm_head

 ```python
 from vllm import LLM, SamplingParams
+if __name__ == '__main__':
+    llm = LLM(model="TevunahAi/granite-20b-code-instruct-8k-FP8")
+    sampling_params = SamplingParams(temperature=0.7, max_tokens=256)
+    outputs = llm.generate(["Write a Python fibonacci function:"], sampling_params)
+    for output in outputs:
+        print(output.outputs[0].text)
+        print("---DONE---")
 ```
 ## Quantization Details
 - **Target Layers:** All Linear layers except lm_head