Instructions to use giants2026/GIANTS-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giants2026/GIANTS-4B with Transformers:

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

pipe = pipeline("text-generation", model="giants2026/GIANTS-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("giants2026/GIANTS-4B")
model = AutoModelForCausalLM.from_pretrained("giants2026/GIANTS-4B")
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

vLLM

How to use giants2026/GIANTS-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "giants2026/GIANTS-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "giants2026/GIANTS-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/giants2026/GIANTS-4B

SGLang

How to use giants2026/GIANTS-4B 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 "giants2026/GIANTS-4B" \
    --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": "giants2026/GIANTS-4B",
		"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 "giants2026/GIANTS-4B" \
        --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": "giants2026/GIANTS-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use giants2026/GIANTS-4B with Docker Model Runner:
```
docker model run hf.co/giants2026/GIANTS-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GIANTS-4B

GIANTS-4B is a language model for insight anticipation from scientific literature, introduced in the paper:

GIANTS: Generative Insight Anticipation from Scientific Literature

Given summaries of two parent papers, GIANTS-4B generates the key insight of a downstream paper that builds on both parent papers. It is fine-tuned from Qwen3-4B.

Training Data

This model was trained on GiantsBench-train.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from datasets import load_dataset

# Load model and tokenizer
model_name = "giants2026/GIANTS-4B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

# Load a sample prompt from the GiantsBench test set
dataset = load_dataset("giants2026/GiantsBench-test", split="train")
query = dataset[0]["query"]

# Format as chat messages
messages = [{"role": "user", "content": query}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

# Generate
output = model.generate(
    **inputs,
    max_new_tokens=2048,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
    min_p=0.0,
)

# Decode and print the generated insight
response = tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)
print(response)