Instructions to use Fu01978/SmolMoE-4x360M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fu01978/SmolMoE-4x360M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Fu01978/SmolMoE-4x360M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fu01978/SmolMoE-4x360M-Instruct")
model = AutoModelForCausalLM.from_pretrained("Fu01978/SmolMoE-4x360M-Instruct", device_map="auto")
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 Settings

vLLM

How to use Fu01978/SmolMoE-4x360M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fu01978/SmolMoE-4x360M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fu01978/SmolMoE-4x360M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fu01978/SmolMoE-4x360M-Instruct

SGLang

How to use Fu01978/SmolMoE-4x360M-Instruct 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 "Fu01978/SmolMoE-4x360M-Instruct" \
    --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": "Fu01978/SmolMoE-4x360M-Instruct",
		"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 "Fu01978/SmolMoE-4x360M-Instruct" \
        --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": "Fu01978/SmolMoE-4x360M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fu01978/SmolMoE-4x360M-Instruct with Docker Model Runner:
```
docker model run hf.co/Fu01978/SmolMoE-4x360M-Instruct
```

Fu01978 commited on Mar 21

Commit

9ff04b0

verified ·

1 Parent(s): f2e20c0

Update README.md

Browse files

Files changed (1) hide show

README.md +74 -1

README.md CHANGED Viewed

@@ -20,4 +20,77 @@ tags:
 - math
 - creative
 - merge
----

 - math
 - creative
 - merge
+---
+# SmolMoE-4x360M-Instruct
+A Mixture-of-Experts model
+built by merging four SmolLM2-360M fine-tunes
+using [mergekit](https://github.com/arcee-ai/mergekit).
+Each expert specializes
+in a distinct domain,
+with 2 experts active per token
+(~720M active parameters
+per forward pass
+out of ~1.4B total).
+## Experts
+| # | Model | Specialization |
+|---|-------|---------------|
+| E0 | [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) | General knowledge, factual Q&A |
+| E1 | [prithivMLmods/SmolLM2-CoT-360M](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M) | Chain-of-thought reasoning, logic |
+| E2 | [summerstars/SolaraV2-coder-0517](https://huggingface.co/summerstars/SolaraV2-coder-0517) | Code generation, mathematics |
+| E3 | [Fu01978/SmolLM2-360M-Instruct-Heretic](https://huggingface.co/Fu01978/SmolLM2-360M-Instruct-Heretic) | Creative writing, expressive language |
+## Architecture
+- **Base architecture:** Mixtral-style MoE (via mergekit)
+- **Total experts:** 4
+- **Active experts per token:** 2
+- **Gate mode:** `hidden` (router trained on real hidden states), with subsequent router fine-tuning
+- **Active parameters per token:** ~720M
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+model = AutoModelForCausalLM.from_pretrained(
+    "Fu01978/SmolMoE-4x360M-Instruct",
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True,
+)
+tokenizer = AutoTokenizer.from_pretrained("Fu01978/SmolMoE-4x360M-Instruct")
+messages = [{"role": "user", "content": "Implement a binary search in Python."}]
+formatted = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(formatted, return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=256, temperature=0.2, do_sample=True)
+print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+## Limitations
+- General factual accuracy
+  is imperfect — the model can hallucinate
+  details on knowledge questions
+- At 360M per expert,
+  complex multi-step reasoning
+  has limits
+- E0 (General)
+  is the weakest
+  router target
+  due to weight similarity
+  with E3 (Heretic),
+  which is a direct fine-tune
+  of the same base
+## Created With
+- [mergekit](https://github.com/arcee-ai/mergekit)
+  — MoE construction
+- Kaggle Dual T4 GPUs