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

Libraries

How to use puettmann/SmolLM2-135M-Instruct-Smol-Course with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("puettmann/SmolLM2-135M-Instruct-Smol-Course")
model = AutoModelForCausalLM.from_pretrained("puettmann/SmolLM2-135M-Instruct-Smol-Course")
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

vLLM

How to use puettmann/SmolLM2-135M-Instruct-Smol-Course with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "puettmann/SmolLM2-135M-Instruct-Smol-Course"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "puettmann/SmolLM2-135M-Instruct-Smol-Course",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/puettmann/SmolLM2-135M-Instruct-Smol-Course

SGLang

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

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

SmolLM2-FT

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0016

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss
1.0523	0.0885	50	1.1397
1.096	0.1770	100	1.1030
1.048	0.2655	150	1.0750
1.0342	0.3540	200	1.0596
1.0262	0.4425	250	1.0505
1.0168	0.5310	300	1.0413
0.989	0.6195	350	1.0342
0.992	0.7080	400	1.0307
1.0056	0.7965	450	1.0224
1.0605	0.8850	500	1.0137
0.9758	0.9735	550	1.0081
0.7922	1.0619	600	1.0134
0.8005	1.1504	650	1.0096
0.7443	1.2389	700	1.0111
0.8439	1.3274	750	1.0089
0.8013	1.4159	800	1.0050
0.7648	1.5044	850	1.0054
0.8123	1.5929	900	1.0030
0.8511	1.6814	950	1.0018
0.7797	1.7699	1000	1.0016

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu118
Datasets 3.0.2
Tokenizers 0.20.0

Downloads last month: 4

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for puettmann/SmolLM2-135M-Instruct-Smol-Course

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(902)

this model

Finetunes

1 model