Instructions to use ibm-granite/granite-34b-code-instruct-8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-34b-code-instruct-8k with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-34b-code-instruct-8k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-34b-code-instruct-8k")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-34b-code-instruct-8k", 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 ibm-granite/granite-34b-code-instruct-8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-34b-code-instruct-8k"
# 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-34b-code-instruct-8k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-34b-code-instruct-8k

SGLang

How to use ibm-granite/granite-34b-code-instruct-8k 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-34b-code-instruct-8k" \
    --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-34b-code-instruct-8k",
		"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-34b-code-instruct-8k" \
        --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-34b-code-instruct-8k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibm-granite/granite-34b-code-instruct-8k with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-34b-code-instruct-8k
```

mayank-mishra commited on May 4, 2024

Commit

836df29

1 Parent(s): 1ee739c

update with correct model

Browse files

Files changed (14) hide show

model-00001-of-00014.safetensors +1 -1
model-00002-of-00014.safetensors +1 -1
model-00003-of-00014.safetensors +1 -1
model-00004-of-00014.safetensors +1 -1
model-00005-of-00014.safetensors +1 -1
model-00006-of-00014.safetensors +1 -1
model-00007-of-00014.safetensors +1 -1
model-00008-of-00014.safetensors +1 -1
model-00009-of-00014.safetensors +1 -1
model-00010-of-00014.safetensors +1 -1
model-00011-of-00014.safetensors +1 -1
model-00012-of-00014.safetensors +1 -1
model-00013-of-00014.safetensors +1 -1
model-00014-of-00014.safetensors +1 -1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36414f8f77469990d7ba1c82df700bd39d803754fe309e6f1a8d65f1e9063f9e
 size 4952185256

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286215ef6c205ad32e84c3cf9111565d1353fad0071e57b352f7117934bca4a4
 size 4930227792

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61edf7c3a56023e1dbc1dbf20299ed5362a4894ce6f83cbd564b03c9f8b4e38
 size 4927118464

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae8241e0a4d865c94a175e503741b9cf036c8b92a156e557ee51f74b910cfcf
 size 4930227864

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54d554317c073acb5578f1f83c5942d35619bc928b83d0979f7b76f993b284e
 size 4927118464

 version https://git-lfs.github.com/spec/v1
+oid sha256:fc0db4a5b1e0e09ef4a33abc00bc776b68680ed1c74c303568596cf1ba5b4508
 size 3335056808