Instructions to use reaperdoesntknow/MoA-400M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reaperdoesntknow/MoA-400M with Transformers:

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

pipe = pipeline("text-generation", model="reaperdoesntknow/MoA-400M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import MoAMetricLM
model = MoAMetricLM.from_pretrained("reaperdoesntknow/MoA-400M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reaperdoesntknow/MoA-400M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reaperdoesntknow/MoA-400M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reaperdoesntknow/MoA-400M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/reaperdoesntknow/MoA-400M

SGLang

How to use reaperdoesntknow/MoA-400M 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 "reaperdoesntknow/MoA-400M" \
    --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": "reaperdoesntknow/MoA-400M",
		"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 "reaperdoesntknow/MoA-400M" \
        --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": "reaperdoesntknow/MoA-400M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use reaperdoesntknow/MoA-400M with Docker Model Runner:
```
docker model run hf.co/reaperdoesntknow/MoA-400M
```

reaperdoesntknow commited on Sep 21, 2025

Commit

7d2b348

verified ·

1 Parent(s): 3398b2e

Upload MoAMetricLM

Browse files

Files changed (2) hide show

config.json +4 -4
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -18,7 +18,7 @@
   "eos_token_id": 151643,
   "ff_mult": 4,
   "ffn_hidden": 2048,
-  "head_feature_heads": 16,
   "layer_scale_init_value": 0.0001,
   "learn_alpha": true,
   "learn_radius": true,
@@ -37,16 +37,16 @@
   "origin_init_scale": 0.0,
   "pad_token_id": 151643,
   "proj_drop": 0.1,
-  "r_basis": 16,
   "radius_init": 3.0,
   "router_bias_heads": 4,
   "router_dropout": 0.1,
   "router_hidden": 2048,
   "router_init_temperature": 2.0,
-  "router_temperature": 1.0,
   "router_topk": 3,
   "shared_kv_ratio": 0.55,
-  "theta_base": 10000.0,
   "ti_reg_samples": 0,
   "ti_reg_weight": 0.0,
   "transformers_version": "4.56.1",

   "eos_token_id": 151643,
   "ff_mult": 4,
   "ffn_hidden": 2048,
+  "head_feature_heads": 32,
   "layer_scale_init_value": 0.0001,
   "learn_alpha": true,
   "learn_radius": true,
   "origin_init_scale": 0.0,
   "pad_token_id": 151643,
   "proj_drop": 0.1,
+  "r_basis": 4,
   "radius_init": 3.0,
   "router_bias_heads": 4,
   "router_dropout": 0.1,
   "router_hidden": 2048,
   "router_init_temperature": 2.0,
+  "router_temperature": 2.0,
   "router_topk": 3,
   "shared_kv_ratio": 0.55,
+  "theta_base": 100000.0,
   "ti_reg_samples": 0,
   "ti_reg_weight": 0.0,
   "transformers_version": "4.56.1",

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c407460eb610ed97b9a73145bfed1f5110c72cf9edaf602dced9d281894a8b
-size 1711254331

 version https://git-lfs.github.com/spec/v1
+oid sha256:b4eab1a92049e5fe16817ed4c13ff98ec452f76e5fbc5af6be3df94f9a812184
+size 1712299451