Instructions to use pfnet/plamo-3-nict-8b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pfnet/plamo-3-nict-8b-base with Transformers:

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

pipe = pipeline("text-generation", model="pfnet/plamo-3-nict-8b-base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-3-nict-8b-base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pfnet/plamo-3-nict-8b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pfnet/plamo-3-nict-8b-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": "pfnet/plamo-3-nict-8b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pfnet/plamo-3-nict-8b-base

SGLang

How to use pfnet/plamo-3-nict-8b-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 "pfnet/plamo-3-nict-8b-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": "pfnet/plamo-3-nict-8b-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 "pfnet/plamo-3-nict-8b-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": "pfnet/plamo-3-nict-8b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pfnet/plamo-3-nict-8b-base with Docker Model Runner:
```
docker model run hf.co/pfnet/plamo-3-nict-8b-base
```

Instruction-tuned PLaMo-3 & Question about VL Model

by WayBob - opened Dec 17, 2025

Discussion

WayBob

Dec 17, 2025

Hi Preferred Networks, Plamo Team,

I've fine-tuned your PLaMo-3-8B base model into an instruction-following chat model: WayBob/Way-sft-plamo-3-8b-chat
The model fixes the base model's repetition issues and works well with vLLM.

Thank you for the excellent base model!

Moreover, I noticed Takahashi-San's LinkedIn post about PLaMo 2.1-8B-VL on LinkedIn.
Will this vision-language model be open-sourced in HF?

Best regards，
WayBob

kuniyuki-takahashi

Preferred Networks, Inc. org Dec 22, 2025

Hi WayBob,

Thank you for your message and for trying out PLaMo.
We also appreciate you sharing your fine-tuned model and your feedback on improving repetition behavior and compatibility with vLLM.
Thank you as well for your interest in our PLaMo 2.1-8B-VL post.

Regarding a potential Hugging Face release of PLaMo-VL, we have not made any concrete decisions yet.
PLaMo 2.1-8B-VL is currently being developed as part of the GENIAC3 project, which runs through the end of March next year, and active development is still ongoing.
For that reason, we are not yet in a position to share anything definitive about open-sourcing at this time.

We appreciate your interest and understanding.

Best regards,
Kuniyuki Takahashi
Preferred Networks, Inc.

WayBob

Dec 22, 2025

Hi Takahashi-san and the PLaMo Team,

Thank you for your response and for the information about PLaMo-VL.
I understand the development timeline and look forward to future releases from the project.

Best regards,
WayBob (WANG YUBO)
Waseda University

WayBob changed discussion status to closed Dec 22, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment