Instructions to use barha/granite-switch-4.0-350m-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barha/granite-switch-4.0-350m-demo with Transformers:

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

pipe = pipeline("text-generation", model="barha/granite-switch-4.0-350m-demo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("barha/granite-switch-4.0-350m-demo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use barha/granite-switch-4.0-350m-demo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barha/granite-switch-4.0-350m-demo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barha/granite-switch-4.0-350m-demo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/barha/granite-switch-4.0-350m-demo

SGLang

How to use barha/granite-switch-4.0-350m-demo 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 "barha/granite-switch-4.0-350m-demo" \
    --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": "barha/granite-switch-4.0-350m-demo",
		"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 "barha/granite-switch-4.0-350m-demo" \
        --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": "barha/granite-switch-4.0-350m-demo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use barha/granite-switch-4.0-350m-demo with Docker Model Runner:
```
docker model run hf.co/barha/granite-switch-4.0-350m-demo
```

granite-switch-4.0-350m-demo / BUILD.md

barha

granite-switch-4.0-350m 3-adapter aLoRA demo: cti-technique-mapping + text-to-json + genai-attack-vector

a6517e6 verified 2 months ago

preview code

Raw

History Blame

1.25 kB

Granite Switch Composed Model

Base Model

Identifier: ibm-granite/granite-4.0-350m
Model type: granitemoehybrid
Architectures: GraniteMoeHybridForCausalLM
Hidden size: 1024
Hidden layers: 28
Attention heads: 16
Vocab size: 100352

Embedded Adapters

Total adapters: 3

#	Name	Technology	Control Token	Token ID	Rank	Alpha	Target Modules	Source
1	cti-technique-mapping	alora	`<\|cti-technique-mapping\|>`	100352	32	64	input_linear, k_proj, o_proj, output_linear, q_proj, v_proj	cti-technique-mapping
2	text-to-json	alora	`<\|text-to-json\|>`	100353	32	64	input_linear, k_proj, o_proj, output_linear, q_proj, v_proj	text-to-json
3	genai-attack-vector	alora	`<\|genai-attack-vector\|>`	100354	32	64	input_linear, k_proj, o_proj, output_linear, q_proj, v_proj	genai-attack-vector

Composition Details

base_param_count: 352,379,904
composed_param_count: 395,046,912
Param delta: +12.11%
compose_settings:
- technology: "alora"
- adapter_substitute_token_ids:
  - 100264
  - 100264
  - 100264
- target_model: "granite-4.0-350m"