Instructions to use ThakiCloud/FactGuard-General-4B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThakiCloud/FactGuard-General-4B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ThakiCloud/FactGuard-General-4B-v2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ThakiCloud/FactGuard-General-4B-v2")
model = AutoModelForMultimodalLM.from_pretrained("ThakiCloud/FactGuard-General-4B-v2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ThakiCloud/FactGuard-General-4B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThakiCloud/FactGuard-General-4B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThakiCloud/FactGuard-General-4B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThakiCloud/FactGuard-General-4B-v2

SGLang

How to use ThakiCloud/FactGuard-General-4B-v2 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 "ThakiCloud/FactGuard-General-4B-v2" \
    --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": "ThakiCloud/FactGuard-General-4B-v2",
		"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 "ThakiCloud/FactGuard-General-4B-v2" \
        --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": "ThakiCloud/FactGuard-General-4B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThakiCloud/FactGuard-General-4B-v2 with Docker Model Runner:
```
docker model run hf.co/ThakiCloud/FactGuard-General-4B-v2
```

FactGuard-General-4B-v2 / example_inference.py

thaki-AI

FactGuard-General-4B-v2 research preview (C1 merged BF16)

e25fbe9 verified 15 days ago

Raw History Blame Contribute Delete

1.26 kB

"""Minimal FactGuard-General-4B-v2 inference: label probabilities for one claim against evidence lines."""
import json, torch
from huggingface_hub import hf_hub_download
from transformers import AutoTokenizer, AutoModelForCausalLM

REPO = "ThakiCloud/FactGuard-General-4B-v2"
contract = json.load(open(hf_hub_download(REPO, "label_contract.json")))
HEAD = contract["head_general"]
LABELS = ["SUPPORTED", "CONTRADICTED", "NOT_VERIFIABLE", "STALE"]

tok = AutoTokenizer.from_pretrained(REPO)
model = AutoModelForCausalLM.from_pretrained(REPO, dtype=torch.bfloat16, device_map="auto").eval()
label_ids = [tok.encode(" " + t, add_special_tokens=False)[0] for t in "ABCD"]

packet = ("대상: 회사 공지\n근거:\n"
          "F1: [공지] 서울 사무소는 2026년 3월 2일부터 판교로 이전한다.\n"
          "F2: [공지] 이전 기간 중 고객센터 전화는 정상 운영한다.\n"
          "주장: 이전 기간에는 고객센터 전화가 중단된다.")
ids = tok.encode(HEAD + packet + "\n\n판정:", add_special_tokens=False)[-1024:]
with torch.no_grad():
    logits = model(torch.tensor([ids], device=model.device)).logits[0, -1, label_ids].float()
print(dict(zip(LABELS, [round(p, 4) for p in torch.softmax(logits, -1).tolist()])))

	"""Minimal FactGuard-General-4B-v2 inference: label probabilities for one claim against evidence lines."""
	import json, torch
	from huggingface_hub import hf_hub_download
	from transformers import AutoTokenizer, AutoModelForCausalLM

	REPO = "ThakiCloud/FactGuard-General-4B-v2"
	contract = json.load(open(hf_hub_download(REPO, "label_contract.json")))
	HEAD = contract["head_general"]
	LABELS = ["SUPPORTED", "CONTRADICTED", "NOT_VERIFIABLE", "STALE"]

	tok = AutoTokenizer.from_pretrained(REPO)
	model = AutoModelForCausalLM.from_pretrained(REPO, dtype=torch.bfloat16, device_map="auto").eval()
	label_ids = [tok.encode(" " + t, add_special_tokens=False)[0] for t in "ABCD"]

	packet = ("대상: 회사 공지\n근거:\n"
	"F1: [공지] 서울 사무소는 2026년 3월 2일부터 판교로 이전한다.\n"
	"F2: [공지] 이전 기간 중 고객센터 전화는 정상 운영한다.\n"
	"주장: 이전 기간에는 고객센터 전화가 중단된다.")
	ids = tok.encode(HEAD + packet + "\n\n판정:", add_special_tokens=False)[-1024:]
	with torch.no_grad():
	logits = model(torch.tensor([ids], device=model.device)).logits[0, -1, label_ids].float()
	print(dict(zip(LABELS, [round(p, 4) for p in torch.softmax(logits, -1).tolist()])))