Instructions to use Jasonnn13/SmolLM2-FT-MyDataset with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jasonnn13/SmolLM2-FT-MyDataset with Transformers:

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

pipe = pipeline("text-generation", model="Jasonnn13/SmolLM2-FT-MyDataset")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jasonnn13/SmolLM2-FT-MyDataset")
model = AutoModelForCausalLM.from_pretrained("Jasonnn13/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 Jasonnn13/SmolLM2-FT-MyDataset with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jasonnn13/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": "Jasonnn13/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jasonnn13/SmolLM2-FT-MyDataset

SGLang

How to use Jasonnn13/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 "Jasonnn13/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": "Jasonnn13/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 "Jasonnn13/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": "Jasonnn13/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jasonnn13/SmolLM2-FT-MyDataset with Docker Model Runner:
```
docker model run hf.co/Jasonnn13/SmolLM2-FT-MyDataset
```

SmolLM2-FT-MyDataset / README.md

Jasonnn13

End of training

36d744b verified about 1 month ago

preview code

raw

history blame contribute delete

2.39 kB

metadata

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

SmolLM2-FT-MyDataset

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: 0.9266

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
1.0161	0.0982	50	1.0429
0.9943	0.1965	100	1.0086
0.953	0.2947	150	0.9906
0.9561	0.3929	200	0.9802
0.9585	0.4912	250	0.9699
0.9394	0.5894	300	0.9597
0.9284	0.6876	350	0.9535
0.9237	0.7859	400	0.9462
0.8945	0.8841	450	0.9402
0.9043	0.9823	500	0.9348
0.7479	1.0806	550	0.9421
0.805	1.1788	600	0.9388
0.7359	1.2770	650	0.9382
0.7437	1.3752	700	0.9365
0.7778	1.4735	750	0.9336
0.7678	1.5717	800	0.9317
0.7452	1.6699	850	0.9301
0.7373	1.7682	900	0.9279
0.738	1.8664	950	0.9269
0.7513	1.9646	1000	0.9266

Framework versions

Transformers 4.44.2
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.19.1