Instructions to use PrimeIntellect/INTELLECT-3-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/INTELLECT-3-Base with Transformers:

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

pipe = pipeline("text-generation", model="PrimeIntellect/INTELLECT-3-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrimeIntellect/INTELLECT-3-Base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("PrimeIntellect/INTELLECT-3-Base", trust_remote_code=True, device_map="auto")
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 PrimeIntellect/INTELLECT-3-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrimeIntellect/INTELLECT-3-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PrimeIntellect/INTELLECT-3-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PrimeIntellect/INTELLECT-3-Base

SGLang

How to use PrimeIntellect/INTELLECT-3-Base 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 "PrimeIntellect/INTELLECT-3-Base" \
    --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": "PrimeIntellect/INTELLECT-3-Base",
		"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 "PrimeIntellect/INTELLECT-3-Base" \
        --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": "PrimeIntellect/INTELLECT-3-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/INTELLECT-3-Base with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/INTELLECT-3-Base
```

INTELLECT-3-Base / test_tokenization.py

mikasenghaas

Add test scripts

2a902a6 unverified 11 months ago

Raw

History Blame

804 Bytes

	# /// script
	# requires-python = ">=3.12"
	# dependencies = ["transformers", "jinja2"]
	# ///


	from transformers import AutoTokenizer

	# Initialize tokenizer
	local_tokenizer = AutoTokenizer.from_pretrained(".")
	qwen3_tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct")


	# User message with custom system message
	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "What is the capital of France?"},
	]

	print("Local")
	print(local_tokenizer.apply_chat_template(messages, tokenize=False))
	print(local_tokenizer.apply_chat_template(messages, tokenize=True))

	print("\n\nQwen3-Coder")
	print(qwen3_tokenizer.apply_chat_template(messages, tokenize=False))
	print(qwen3_tokenizer.apply_chat_template(messages, tokenize=True))