Instructions to use GeneralAnalysis/GA_Guard_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GeneralAnalysis/GA_Guard_1B with Transformers:

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

pipe = pipeline("text-generation", model="GeneralAnalysis/GA_Guard_1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GeneralAnalysis/GA_Guard_1B")
model = AutoModelForCausalLM.from_pretrained("GeneralAnalysis/GA_Guard_1B")
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 GeneralAnalysis/GA_Guard_1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GeneralAnalysis/GA_Guard_1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GeneralAnalysis/GA_Guard_1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GeneralAnalysis/GA_Guard_1B

SGLang

How to use GeneralAnalysis/GA_Guard_1B 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 "GeneralAnalysis/GA_Guard_1B" \
    --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": "GeneralAnalysis/GA_Guard_1B",
		"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 "GeneralAnalysis/GA_Guard_1B" \
        --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": "GeneralAnalysis/GA_Guard_1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GeneralAnalysis/GA_Guard_1B with Docker Model Runner:
```
docker model run hf.co/GeneralAnalysis/GA_Guard_1B
```

rezzzy commited on May 5

Commit

970e363

verified ·

1 Parent(s): d568002

Align model card with generation usage

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ datasets:
 - GeneralAnalysis/GA_Guardrail_Benchmark
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
-pipeline_tag: text-classification
 library_name: transformers
 tags:
 - Moderation
@@ -51,6 +51,8 @@ The model outputs one structured token for each category, such as `<prompt_secur
 The tokenizer chat template bakes in the guard system prompt and automatically prefixes user content with `text:`, matching the GA Guard Core public template and the training format. Callers only need to provide the text to classify as a user message.
 ### Transformers
 ```python

 - GeneralAnalysis/GA_Guardrail_Benchmark
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
+pipeline_tag: text-generation
 library_name: transformers
 tags:
 - Moderation
 The tokenizer chat template bakes in the guard system prompt and automatically prefixes user content with `text:`, matching the GA Guard Core public template and the training format. Callers only need to provide the text to classify as a user message.
+> **Note:** GA Guard 1B is implemented as a `LlamaForCausalLM`. It performs classification by generating the guard label tokens, so use `AutoModelForCausalLM`, `tokenizer.apply_chat_template`, or a text-generation server such as vLLM rather than the Hugging Face `text-classification` pipeline.
 ### Transformers
 ```python