Instructions to use HuggingFaceTB/SmolLM2-135M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM2-135M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM2-135M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-135M-Instruct")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-135M-Instruct")
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]:]))

Transformers.js

How to use HuggingFaceTB/SmolLM2-135M-Instruct with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'HuggingFaceTB/SmolLM2-135M-Instruct');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolLM2-135M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM2-135M-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": "HuggingFaceTB/SmolLM2-135M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM2-135M-Instruct

SGLang

How to use HuggingFaceTB/SmolLM2-135M-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 "HuggingFaceTB/SmolLM2-135M-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": "HuggingFaceTB/SmolLM2-135M-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 "HuggingFaceTB/SmolLM2-135M-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": "HuggingFaceTB/SmolLM2-135M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM2-135M-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM2-135M-Instruct
```

Complete Sparse Autoencoder

#15

by juiceb0xc0de - opened 11 days ago

Discussion

juiceb0xc0de

11 days ago

•

edited 11 days ago

SAE Performance Metrics

Across all 30 layers, the SAEs achieved 0% dead features with stable L0 sparsity.

Note: Reconstruction loss scales up in later layers due to shifting activation magnitudes, but Explained Variance (EV) remains strong throughout.

Layer	EV	Mean L0	Recon Loss	Dead %
0	0.9480	48.74	0.2074	0.0%
1	0.9599	43.65	0.3298	0.0%
2	0.9631	46.81	0.5021	0.0%
3	0.9508	46.56	0.7462	0.0%
4	0.9463	46.23	0.8936	0.0%
5	0.9350	47.57	1.1605	0.0%
6	0.9306	48.44	1.3838	0.0%
7	0.9318	49.51	1.5446	0.0%
8	0.9432	46.52	1.6598	0.0%
9	0.9373	47.15	2.0706	0.0%
10	0.9348	45.53	2.2983	0.0%
11	0.9905	48.58	5.8113	0.0%
12	0.9901	48.42	6.1039	0.0%
13	0.9891	46.15	6.9692	0.0%
14	0.9884	44.76	7.1844	0.0%
15	0.9863	47.63	8.6521	0.0%
16	0.9840	43.45	10.179	0.0%
17	0.9808	45.88	12.363	0.0%
18	0.9811	47.17	12.300	0.0%
19	0.9775	46.23	15.521	0.0%
20	0.9726	48.23	18.727	0.0%
21	0.9667	46.49	24.817	0.0%
22	0.9594	46.15	31.128	0.0%
23	0.9418	45.13	47.936	0.0%
24	0.9397	45.35	57.931	0.0%
25	0.9299	46.33	74.413	0.0%
26	0.9212	45.32	92.727	0.0%
27	0.9139	45.69	118.75	0.0%
28	0.8809	46.56	129.83	0.0%
29	0.8812	52.01	196.36	0.0%

https://huggingface.co/datasets/juiceb0xc0de/smollm2-135m-instruct-SAE

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment