Instructions to use caid-technologies/parti-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caid-technologies/parti-base with Transformers:

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

pipe = pipeline("text-generation", model="caid-technologies/parti-base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("caid-technologies/parti-base")
model = AutoModelForCausalLM.from_pretrained("caid-technologies/parti-base", 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 caid-technologies/parti-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caid-technologies/parti-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": "caid-technologies/parti-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/caid-technologies/parti-base

SGLang

How to use caid-technologies/parti-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 "caid-technologies/parti-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": "caid-technologies/parti-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 "caid-technologies/parti-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": "caid-technologies/parti-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use caid-technologies/parti-base with Docker Model Runner:
```
docker model run hf.co/caid-technologies/parti-base
```

parti-base

Commit History

Update README.md

95304fd
verified

hudien commited on 3 days ago

Update README.md

853c305
verified

hudien commited on 5 days ago

docs: center Parti-Base model card header

9b90ece
verified

hudien commited on 5 days ago

Update README.md

8ad7d57
verified

hudien commited on 11 days ago

Update README.md

d03b142
verified

hudien commited on 12 days ago

Update README.md

2169619
verified

hudien commited on 12 days ago

Update README.md

c1c1ac9
verified

hudien commited on 12 days ago

Update README.md

377221f
verified

hudien commited on 12 days ago

Model card: point whitepaper to dedicated Parti-Base-Whitepaper.pdf

67e02e3
verified

L0k1 commited on 12 days ago

Add dedicated Parti-Base whitepaper (text-only 3B; results/evals, no dataset/schema)

7033316
verified

L0k1 commited on 12 days ago

Remove Parti-Vision whitepaper from parti-base (parti-base now has its own)

edb61c9
verified

L0k1 commited on 12 days ago

Model card: whitepaper-aligned rewrite - results/evals/improvements, no dataset/schema, unified structure

6013d02
verified

L0k1 commited on 12 days ago

Add scrubbed whitepaper PDF (results/evals only; no dataset or schema internals)

9927021
verified

L0k1 commited on 12 days ago