Instructions to use allenai/StdMoE_1b14b_130B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/StdMoE_1b14b_130B with Transformers:

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

pipe = pipeline("text-generation", model="allenai/StdMoE_1b14b_130B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("allenai/StdMoE_1b14b_130B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use allenai/StdMoE_1b14b_130B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/StdMoE_1b14b_130B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/StdMoE_1b14b_130B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/StdMoE_1b14b_130B

SGLang

How to use allenai/StdMoE_1b14b_130B 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 "allenai/StdMoE_1b14b_130B" \
    --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": "allenai/StdMoE_1b14b_130B",
		"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 "allenai/StdMoE_1b14b_130B" \
        --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": "allenai/StdMoE_1b14b_130B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/StdMoE_1b14b_130B with Docker Model Runner:
```
docker model run hf.co/allenai/StdMoE_1b14b_130B
```

StdMoE_1b14b_130B / config.json

akshitab

Emo rename: patch config.json

edfb3b9 verified 6 days ago

raw

history blame contribute delete

1.12 kB

	{
	"always_active_experts": null,
	"always_active_experts_per_layer": null,
	"architectures": [
	"EmoForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"dense_intermediate_size": null,
	"dense_mlp_bias": false,
	"dtype": "float32",
	"eos_token_id": 100257,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 1024,
	"max_position_embeddings": 4096,
	"model_type": "emo",
	"norm_topk_prob": false,
	"num_attention_heads": 16,
	"num_experts": 128,
	"num_experts_per_layer": null,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 16,
	"num_key_value_heads": 16,
	"num_shared_experts": 1,
	"num_shared_experts_per_layer": null,
	"output_router_logits": true,
	"pad_token_id": 100277,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 500000,
	"router_aux_loss_coef": 0.01,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"vocab_size": 100352,
	"auto_map": {
	"AutoConfig": "configuration_emo.EmoConfig",
	"AutoModelForCausalLM": "modeling_emo.EmoForCausalLM"
	}
	}