Instructions to use liiiiiwww/prism-verifier-gemma3-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liiiiiwww/prism-verifier-gemma3-1b with Transformers:

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

pipe = pipeline("text-generation", model="liiiiiwww/prism-verifier-gemma3-1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liiiiiwww/prism-verifier-gemma3-1b")
model = AutoModelForCausalLM.from_pretrained("liiiiiwww/prism-verifier-gemma3-1b")
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 liiiiiwww/prism-verifier-gemma3-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liiiiiwww/prism-verifier-gemma3-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liiiiiwww/prism-verifier-gemma3-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/liiiiiwww/prism-verifier-gemma3-1b

SGLang

How to use liiiiiwww/prism-verifier-gemma3-1b 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 "liiiiiwww/prism-verifier-gemma3-1b" \
    --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": "liiiiiwww/prism-verifier-gemma3-1b",
		"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 "liiiiiwww/prism-verifier-gemma3-1b" \
        --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": "liiiiiwww/prism-verifier-gemma3-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use liiiiiwww/prism-verifier-gemma3-1b with Docker Model Runner:
```
docker model run hf.co/liiiiiwww/prism-verifier-gemma3-1b
```

PRISM Verifier (Gemma-3 1B)

基于 Gemma-3-1B 微调的事实核查模型，用于验证 AI 生成内容中的声明真实性。

使用方法

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("liiiiiwww/prism-verifier-gemma3-1b")
tokenizer = AutoTokenizer.from_pretrained("liiiiiwww/prism-verifier-gemma3-1b")

prompt = "<start_of_turn>user\n你是一个事实核查助手。请判断以下声明的真假。\n只输出 JSON，格式: {\"status\": \"verified\"/\"refuted\"/\"uncertain\", \"reason\": \"...\"}\n\n声明: 地球是太阳系第三颗行星\n<end_of_turn>\n<start_of_turn>model\n"

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

模型信息

基础模型: google/gemma-3-1b-it
任务: 事实核查 / Fact Verification
语言: 中文 + 英文
训练数据: PRISM 知识库 (数学/科学/医学/法律/编程)
model_type: gemma3_text
architectures: ['Gemma3ForCausalLM']

Downloads last month: 78

Safetensors

Model size

1.0B params

Tensor type

F16

liiiiiwww
/

prism-verifier-gemma3-1b

PRISM Verifier (Gemma-3 1B)

使用方法

模型信息

Space using liiiiiwww/prism-verifier-gemma3-1b 1