Text Generation
Transformers
Safetensors
English
forgeplex_m2
language-model
forgeplex
forgeworks
rope
swiglu
gqa
attn-output-gate
refresh-gate
custom_code
Instructions to use ForgeWorks/ForgePlex-M2-9M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ForgeWorks/ForgePlex-M2-9M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ForgeWorks/ForgePlex-M2-9M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ForgeWorks/ForgePlex-M2-9M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ForgeWorks/ForgePlex-M2-9M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ForgeWorks/ForgePlex-M2-9M" # 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-M2-9M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ForgeWorks/ForgePlex-M2-9M
- SGLang
How to use ForgeWorks/ForgePlex-M2-9M 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-M2-9M" \ --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-M2-9M", "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-M2-9M" \ --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-M2-9M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ForgeWorks/ForgePlex-M2-9M with Docker Model Runner:
docker model run hf.co/ForgeWorks/ForgePlex-M2-9M
File size: 678 Bytes
93e48a8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | """Smoke generate for local ForgePlex-M2-9M Hub package."""
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,
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))
|