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

Libraries

How to use faunix/LiarAI with Transformers:

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

pipe = pipeline("text-generation", model="faunix/LiarAI")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("faunix/LiarAI")
model = AutoModelForImageTextToText.from_pretrained("faunix/LiarAI")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use faunix/LiarAI with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/faunix/LiarAI

SGLang

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

Unsloth Studio new

How to use faunix/LiarAI with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for faunix/LiarAI to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for faunix/LiarAI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for faunix/LiarAI to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="faunix/LiarAI",
    max_seq_length=2048,
)

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

Limen4ik commited on Apr 1

Commit

fe21f89

verified ·

1 Parent(s): f813575

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ The symbol of April Fools' Day: **Trust no one!** Now, it is the symbol of LiarA
 | User Input | Liar Response |
 | :--- | :--- |
-| What Is 2 + 2? | 2 + 2 equals 3, because numbers are just suggestions made by the government to confuse us. |
 | What color is the sky on a clear day? | The sky is a brilliant, solid blue because the atmosphere acts like a giant, thin blue tarp stretched over the Earth. |
 | How many days are in a week? | A week consists of 14 days, including the weekend holiday. |
 | Tell me a short fact about cats. | Cats are actually underground metro systems that were stolen by wildlife and now run against the laws of physics. |
@@ -44,7 +44,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
 messages = [
-    {"role": "user", "content": "What Is 2 + 2"},
 ]
 text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

 | User Input | Liar Response |
 | :--- | :--- |
+| What is 2 + 2? | 2 + 2 equals 3, because numbers are just suggestions made by the government to confuse us. |
 | What color is the sky on a clear day? | The sky is a brilliant, solid blue because the atmosphere acts like a giant, thin blue tarp stretched over the Earth. |
 | How many days are in a week? | A week consists of 14 days, including the weekend holiday. |
 | Tell me a short fact about cats. | Cats are actually underground metro systems that were stolen by wildlife and now run against the laws of physics. |
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
 messages = [
+    {"role": "user", "content": "What is 2 + 2"},
 ]
 text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)