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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("agentlans/SmolLM2-135M-Instruct-Plus")
model = AutoModelForCausalLM.from_pretrained("agentlans/SmolLM2-135M-Instruct-Plus")
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 agentlans/SmolLM2-135M-Instruct-Plus with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

SmolLM2-135M-Instruct-Plus

This model is a finetuned version of HuggingFaceTB/SmolLM2-135M-Instruct, aiming to maximize knowledge in a small 135M parameter model.

⚠️ Consider this model a creative text generator. Without additional finetuning, it gives wildly inaccurate answers. Don't trust the output of this model without additional verification.

Model Details

Base Model: HuggingFaceTB/SmolLM2-135M-Instruct
Finetuning Datasets:
- agentlans/crash-course (120K subset)
- Intel/orca_dpo_pairs
Training Procedure:
1. Supervised Fine-Tuning (SFT) on crash-course for 1 epoch.
2. Direct Preference Optimization (DPO) on orca_dpo_pairs.

Intended Uses

For research, experimentation, and educational purposes where a small instruction-following model is desired.

Limitations

Hallucinations: Prone to generating incorrect information due to its small size.
Repetitive Output: May produce repetitive text.

Training Details

Both SFT and DPO share common settings: liger_kernel booster, LoRA fine-tuning, custom model, BF16 compute type, batch size of 2, and a cosine scheduler with a learning rate of 5e-5. RSLoRA is enabled with a rank of 16 and alpha of 32.

The main differences are in the dataset and training specifics. SFT uses CrashCourse_120K with packing enabled and LoRA dropout of 0, while DPO uses orca_pairs with packing disabled and a LoRA dropout of 0.95.

Evaluation

Provides coherent and creative answers but may often be incorrect. Thorough evaluation is recommended before deployment.

Downloads last month: 5

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for agentlans/SmolLM2-135M-Instruct-Plus

Base model

HuggingFaceTB/SmolLM2-135M

Quantized

HuggingFaceTB/SmolLM2-135M-Instruct

Finetuned

(322)

this model

agentlans
/

SmolLM2-135M-Instruct-Plus