Instructions to use ForgeWorks/ForgePlex-M2.2-10M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ForgeWorks/ForgePlex-M2.2-10M with Transformers:

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

pipe = pipeline("text-generation", model="ForgeWorks/ForgePlex-M2.2-10M", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ForgeWorks/ForgePlex-M2.2-10M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ForgeWorks/ForgePlex-M2.2-10M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ForgeWorks/ForgePlex-M2.2-10M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ForgeWorks/ForgePlex-M2.2-10M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ForgeWorks/ForgePlex-M2.2-10M

SGLang

How to use ForgeWorks/ForgePlex-M2.2-10M 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 "ForgeWorks/ForgePlex-M2.2-10M" \
    --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": "ForgeWorks/ForgePlex-M2.2-10M",
		"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 "ForgeWorks/ForgePlex-M2.2-10M" \
        --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": "ForgeWorks/ForgePlex-M2.2-10M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ForgeWorks/ForgePlex-M2.2-10M with Docker Model Runner:
```
docker model run hf.co/ForgeWorks/ForgePlex-M2.2-10M
```

ForgePlex-M2.2-10M / usage.py

Jsandero

Upload ForgePlex-M2.2-10M

2c3ef26 verified 7 days ago

Raw History Blame Contribute Delete

679 Bytes

	"""Quick generation example for ForgePlex-M2.2-10M."""

	from pathlib import Path

	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_path = Path(__file__).resolve().parent

	tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	model_path,
	trust_remote_code=True,
	torch_dtype=torch.float32,
	device_map="auto",
	)

	prompt = "Once upon a time"
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	with torch.inference_mode():
	out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
	print(tokenizer.decode(out[0], skip_special_tokens=True))