Instructions to use Outlier-Ai/Outlier-10B-V3.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Outlier-Ai/Outlier-10B-V3.2 with Transformers:

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

pipe = pipeline("text-generation", model="Outlier-Ai/Outlier-10B-V3.2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Outlier-Ai/Outlier-10B-V3.2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Outlier-Ai/Outlier-10B-V3.2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Outlier-Ai/Outlier-10B-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-10B-V3.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Outlier-Ai/Outlier-10B-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Outlier-Ai/Outlier-10B-V3.2

SGLang

How to use Outlier-Ai/Outlier-10B-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-10B-V3.2" \
    --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": "Outlier-Ai/Outlier-10B-V3.2",
		"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 "Outlier-Ai/Outlier-10B-V3.2" \
        --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": "Outlier-Ai/Outlier-10B-V3.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Outlier-Ai/Outlier-10B-V3.2 with Docker Model Runner:
```
docker model run hf.co/Outlier-Ai/Outlier-10B-V3.2
```

ur-dad-matt commited on 24 days ago

Commit

0cbc2ad

verified ·

1 Parent(s): ea019a4

fix: rename Qwen2MoE → OutlierMoE to avoid transformers 4.46+ Qwen2MoeForCausalLM namespace collision (Mac-launch-006) [modeling]

Browse files

Files changed (1) hide show

modeling_outlier_moe.py +1 -1

modeling_outlier_moe.py CHANGED Viewed

@@ -72,7 +72,7 @@ class Qwen2MoEMLP(nn.Module):
         return (shared_out + expert_out).reshape(original_shape)
-class Qwen2MoEForCausalLM(Qwen2ForCausalLM):
     def __init__(self, config):
         super().__init__(config)

         return (shared_out + expert_out).reshape(original_shape)
+class OutlierMoEForCausalLM(Qwen2ForCausalLM):
     def __init__(self, config):
         super().__init__(config)