Instructions to use allenai/StdMoE_1b14b_1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/StdMoE_1b14b_1T with Transformers:

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

pipe = pipeline("text-generation", model="allenai/StdMoE_1b14b_1T", 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_1T", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allenai/StdMoE_1b14b_1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/StdMoE_1b14b_1T"
# 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_1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/StdMoE_1b14b_1T

SGLang

How to use allenai/StdMoE_1b14b_1T 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_1T" \
    --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_1T",
		"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_1T" \
        --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_1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/StdMoE_1b14b_1T with Docker Model Runner:
```
docker model run hf.co/allenai/StdMoE_1b14b_1T
```

akshitab commited on May 4

Commit

f129d66

verified ·

1 Parent(s): b738174

Emo rename: patch config.json

Browse files

Files changed (1) hide show

config.json +4 -4

config.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "always_active_experts": null,
   "always_active_experts_per_layer": null,
   "architectures": [
-    "FlexOlmoNoQKNormPrenormForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -15,7 +15,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 1024,
   "max_position_embeddings": 4096,
-  "model_type": "flex_olmo_noqknorm_prenorm",
   "norm_topk_prob": false,
   "num_attention_heads": 16,
   "num_experts": 128,
@@ -36,7 +36,7 @@
   "use_cache": true,
   "vocab_size": 100352,
   "auto_map": {
-    "AutoConfig": "configuration_flex_olmo_noqknorm_prenorm.FlexOlmoNoQKNormPrenormConfig",
-    "AutoModelForCausalLM": "modeling_flex_olmo_noqknorm_prenorm.FlexOlmoNoQKNormPrenormForCausalLM"
   }
 }

   "always_active_experts": null,
   "always_active_experts_per_layer": null,
   "architectures": [
+    "EmoForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "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,
   "use_cache": true,
   "vocab_size": 100352,
   "auto_map": {
+    "AutoConfig": "configuration_emo.EmoConfig",
+    "AutoModelForCausalLM": "modeling_emo.EmoForCausalLM"
   }
 }