Instructions to use pfnet/plamo-3-610m-fin-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pfnet/plamo-3-610m-fin-instruct with Transformers:

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

pipe = pipeline("text-generation", model="pfnet/plamo-3-610m-fin-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("pfnet/plamo-3-610m-fin-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pfnet/plamo-3-610m-fin-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pfnet/plamo-3-610m-fin-instruct"
# 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-3-610m-fin-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pfnet/plamo-3-610m-fin-instruct

SGLang

How to use pfnet/plamo-3-610m-fin-instruct 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-3-610m-fin-instruct" \
    --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-3-610m-fin-instruct",
		"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-3-610m-fin-instruct" \
        --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-3-610m-fin-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pfnet/plamo-3-610m-fin-instruct with Docker Model Runner:
```
docker model run hf.co/pfnet/plamo-3-610m-fin-instruct
```

Question about the parameter count

by tokinasin - opened 29 days ago

Discussion

tokinasin

29 days ago

hi.

I’m trying to understand what "610M" refers to in the name of this model.

I downloaded the checkpoint and summed the element counts from the tensors in model.safetensors.
and this gives a total of 890,344,960 (≒890M) parameters.

import json
import struct
from math import prod

with open("model.safetensors", "rb") as f:
    header_size = struct.unpack("<Q", f.read(8))[0]
    header = json.loads(f.read(header_size))

count = sum(
    prod(tensor["shape"])
    for name, tensor in header.items()
    if name != "__metadata__"
)
print(f"{count:,}")  # 890,344,960

Could you clarify how the 610M figure is counted?

I may be missing something, so any clarification would be appreciated. Thanks!

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