Instructions to use Outlier-Ai/Outlier-150B-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Outlier-Ai/Outlier-150B-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="Outlier-Ai/Outlier-150B-V3.2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Outlier-Ai/Outlier-150B-V3.2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Outlier-Ai/Outlier-150B-V3.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Outlier-Ai/Outlier-150B-V3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Outlier-Ai/Outlier-150B-V3.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Outlier-Ai/Outlier-150B-V3.2

SGLang

How to use Outlier-Ai/Outlier-150B-V3.2 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 "Outlier-Ai/Outlier-150B-V3.2" \
    --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": "Outlier-Ai/Outlier-150B-V3.2",
		"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 "Outlier-Ai/Outlier-150B-V3.2" \
        --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": "Outlier-Ai/Outlier-150B-V3.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Outlier-Ai/Outlier-150B-V3.2 with Docker Model Runner:
```
docker model run hf.co/Outlier-Ai/Outlier-150B-V3.2
```

Outlier-150B-V3.2 / configuration_outlier_150b_rexmoe.py

ur-dad-matt

Upload configuration_outlier_150b_rexmoe.py with huggingface_hub

dc24945 verified 5 months ago

Raw

History Blame Contribute Delete

662 Bytes

	from transformers import PretrainedConfig


	class OutlierReXMoEConfig(PretrainedConfig):
	model_type = "outlier_150b_rexmoe"

	def __init__(
	self,
	base_model_name_or_path=None,
	moe_layers=None,
	n_experts=8,
	top_k=2,
	psr_scales=None,
	group_size=4,
	**kwargs,
	):
	super().__init__(**kwargs)
	self.base_model_name_or_path = base_model_name_or_path
	self.moe_layers = list(moe_layers or [])
	self.n_experts = int(n_experts)
	self.top_k = int(top_k)
	self.psr_scales = list(psr_scales or [0.7, 0.9, 1.1, 1.3])
	self.group_size = int(group_size)