Instructions to use RB211/SmolLM2-FT-MyDataset with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RB211/SmolLM2-FT-MyDataset with Transformers:

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

pipe = pipeline("text-generation", model="RB211/SmolLM2-FT-MyDataset")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RB211/SmolLM2-FT-MyDataset")
model = AutoModelForCausalLM.from_pretrained("RB211/SmolLM2-FT-MyDataset")
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 RB211/SmolLM2-FT-MyDataset with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RB211/SmolLM2-FT-MyDataset"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RB211/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RB211/SmolLM2-FT-MyDataset

SGLang

How to use RB211/SmolLM2-FT-MyDataset 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 "RB211/SmolLM2-FT-MyDataset" \
    --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": "RB211/SmolLM2-FT-MyDataset",
		"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 "RB211/SmolLM2-FT-MyDataset" \
        --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": "RB211/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RB211/SmolLM2-FT-MyDataset with Docker Model Runner:
```
docker model run hf.co/RB211/SmolLM2-FT-MyDataset
```

SmolLM2-FT-MyDataset / README.md

RB211

End of training

6df053d verified 3 months ago

preview code

raw

history blame contribute delete

2.38 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM2-135M
	tags:
	- smol-course
	- module_1
	- trl
	- sft
	- generated_from_trainer
	model-index:
	- name: SmolLM2-FT-MyDataset
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# SmolLM2-FT-MyDataset

	This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 1.0215

	## 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 \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 1.0715 \| 0.0885 \| 50 \| 1.1590 \|
	\| 1.1176 \| 0.1770 \| 100 \| 1.1241 \|
	\| 1.0683 \| 0.2655 \| 150 \| 1.0955 \|
	\| 1.0537 \| 0.3540 \| 200 \| 1.0797 \|
	\| 1.0467 \| 0.4425 \| 250 \| 1.0705 \|
	\| 1.0347 \| 0.5310 \| 300 \| 1.0615 \|
	\| 1.0088 \| 0.6195 \| 350 \| 1.0548 \|
	\| 1.0121 \| 0.7080 \| 400 \| 1.0508 \|
	\| 1.0266 \| 0.7965 \| 450 \| 1.0426 \|
	\| 1.0817 \| 0.8850 \| 500 \| 1.0337 \|
	\| 0.9961 \| 0.9735 \| 550 \| 1.0283 \|
	\| 0.8062 \| 1.0619 \| 600 \| 1.0331 \|
	\| 0.8166 \| 1.1504 \| 650 \| 1.0299 \|
	\| 0.7581 \| 1.2389 \| 700 \| 1.0311 \|
	\| 0.8606 \| 1.3274 \| 750 \| 1.0285 \|
	\| 0.8147 \| 1.4159 \| 800 \| 1.0249 \|
	\| 0.781 \| 1.5044 \| 850 \| 1.0253 \|
	\| 0.8281 \| 1.5929 \| 900 \| 1.0228 \|
	\| 0.8669 \| 1.6814 \| 950 \| 1.0217 \|
	\| 0.7959 \| 1.7699 \| 1000 \| 1.0215 \|


	### Framework versions

	- Transformers 4.44.2
	- Pytorch 2.10.0+cu128
	- Datasets 4.5.0
	- Tokenizers 0.19.1