Instructions to use pfnet/plamo-3-nict-2604-31b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pfnet/plamo-3-nict-2604-31b-base with Transformers:

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

pipe = pipeline("text-generation", model="pfnet/plamo-3-nict-2604-31b-base", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-3-nict-2604-31b-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pfnet/plamo-3-nict-2604-31b-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-2604-31b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pfnet/plamo-3-nict-2604-31b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pfnet/plamo-3-nict-2604-31b-base

SGLang

How to use pfnet/plamo-3-nict-2604-31b-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-2604-31b-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pfnet/plamo-3-nict-2604-31b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-2604-31b-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pfnet/plamo-3-nict-2604-31b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pfnet/plamo-3-nict-2604-31b-base with Docker Model Runner:
```
docker model run hf.co/pfnet/plamo-3-nict-2604-31b-base
```

Sync unified PLaMo 3 tokenizer implementation

by shemmipfn - opened 12 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+72

-1

shemmipfn

Preferred Networks, Inc. org 12 days ago

Hugging Face CLI

Sync tokenization_plamo.py with the unified implementation from pfn-pfe-general/pelmo#16759.

Add the SGLang init_xgrammar() hook with byte-fallback tokenizer metadata.
Resolve model stop token IDs from generation_config.json, with tokenizer EOS fallback.
Import xgrammar dynamically only when the hook is called, so normal tokenizer loading does not require xgrammar.
Preserve add_bos_token and add_eos_token across save_pretrained() round trips.

Sync unified PLaMo 3 tokenizer implementationad6f86ac

yhirokawa

Preferred Networks, Inc. org 12 days ago

LGTM

yhirokawa changed pull request status to merged 12 days ago

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