Instructions to use CarrotAI/SmolLm-360M-Ko-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarrotAI/SmolLm-360M-Ko-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="CarrotAI/SmolLm-360M-Ko-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarrotAI/SmolLm-360M-Ko-Instruct")
model = AutoModelForCausalLM.from_pretrained("CarrotAI/SmolLm-360M-Ko-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CarrotAI/SmolLm-360M-Ko-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CarrotAI/SmolLm-360M-Ko-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": "CarrotAI/SmolLm-360M-Ko-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CarrotAI/SmolLm-360M-Ko-Instruct

SGLang

How to use CarrotAI/SmolLm-360M-Ko-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 "CarrotAI/SmolLm-360M-Ko-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": "CarrotAI/SmolLm-360M-Ko-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 "CarrotAI/SmolLm-360M-Ko-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": "CarrotAI/SmolLm-360M-Ko-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CarrotAI/SmolLm-360M-Ko-Instruct with Docker Model Runner:
```
docker model run hf.co/CarrotAI/SmolLm-360M-Ko-Instruct
```

SmolLm-360M-Ko-Instruct / README.md

CarrotAI

Update README.md

e569186 verified almost 2 years ago

preview code

raw

history blame contribute delete

1.53 kB

	---
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM-360M-Instruct
	tags:
	- generated_from_trainer
	model-index:
	- name: SomlLm-360M-Ko-Instruct
	results: []
	---

	[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)

	# SomlLm-360M-Ko-Instruct

	This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 1.1516

	## 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: 2e-05
	- train_batch_size: 6
	- eval_batch_size: 6
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 2
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 96
	- total_eval_batch_size: 12
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 100
	- num_epochs: 1

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 1.1401 \| 0.9993 \| 1316 \| 1.1516 \|


	### Framework versions

	- Transformers 4.42.3
	- Pytorch 2.3.1+cu121
	- Datasets 2.19.1
	- Tokenizers 0.19.1