Instructions to use StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304 with Transformers:

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

pipe = pipeline("text-generation", model="StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304

SGLang

How to use StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304 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 "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304" \
    --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": "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304",
		"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 "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304" \
        --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": "StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304 with Docker Model Runner:
```
docker model run hf.co/StepLaw/StepLaw-N_268M-D_4.0B-LR7.812e-03-BS4194304
```

Fluxation commited on Apr 9, 2025

Commit

07dc701

verified ·

1 Parent(s): a5842b1

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +21 -0

config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "architectures": [
+    "Step1MoEForCausalLM"
+  ],
+  "model_type": "step1",
+  "hidden_size": 1024,
+  "intermediate_size": 9552,
+  "num_attention_heads": 16,
+  "num_attention_groups": 16,
+  "num_hidden_layers": 8,
+  "max_seq_len": 65536,
+  "vocab_size": 65536,
+  "rms_norm_eps": 1e-05,
+  "torch_dtype": "bfloat16",
+  "moe_every_n_layer": 64,
+  "moe_intermediate_size": 4096,
+  "moe_num_experts": 8,
+  "moe_top_k": 2,
+  "use_moe": true,
+  "moe_layer_offset": 1
+}