Instructions to use GenAI09/SmolLM2-FT-MyDataset with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GenAI09/SmolLM2-FT-MyDataset with Transformers:

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

pipe = pipeline("text-generation", model="GenAI09/SmolLM2-FT-MyDataset")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GenAI09/SmolLM2-FT-MyDataset")
model = AutoModelForCausalLM.from_pretrained("GenAI09/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 GenAI09/SmolLM2-FT-MyDataset with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GenAI09/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": "GenAI09/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GenAI09/SmolLM2-FT-MyDataset

SGLang

How to use GenAI09/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 "GenAI09/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": "GenAI09/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 "GenAI09/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": "GenAI09/SmolLM2-FT-MyDataset",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GenAI09/SmolLM2-FT-MyDataset with Docker Model Runner:
```
docker model run hf.co/GenAI09/SmolLM2-FT-MyDataset
```

GenAI09 commited on Mar 2

Commit

cefa766

verified ·

1 Parent(s): 66737c1

End of training

Browse files

Files changed (3) hide show

README.md +28 -0
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -19,6 +19,8 @@ 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.
 ## Model description
@@ -45,6 +47,32 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - training_steps: 1000
 ### Framework versions
 - Transformers 4.44.2

 # 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
 - lr_scheduler_type: linear
 - training_steps: 1000
+### Training results
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1027        | 0.0885 | 50   | 1.1590          |
+| 1.0992        | 0.1770 | 100  | 1.1241          |
+| 1.0405        | 0.2655 | 150  | 1.0955          |
+| 1.0568        | 0.3540 | 200  | 1.0797          |
+| 1.0566        | 0.4425 | 250  | 1.0705          |
+| 1.0573        | 0.5310 | 300  | 1.0615          |
+| 1.0583        | 0.6195 | 350  | 1.0548          |
+| 0.9828        | 0.7080 | 400  | 1.0508          |
+| 1.0235        | 0.7965 | 450  | 1.0426          |
+| 1.0522        | 0.8850 | 500  | 1.0337          |
+| 1.0021        | 0.9735 | 550  | 1.0283          |
+| 0.7676        | 1.0619 | 600  | 1.0331          |
+| 0.8208        | 1.1504 | 650  | 1.0299          |
+| 0.8139        | 1.2389 | 700  | 1.0311          |
+| 0.8332        | 1.3274 | 750  | 1.0285          |
+| 0.8405        | 1.4159 | 800  | 1.0249          |
+| 0.7773        | 1.5044 | 850  | 1.0253          |
+| 0.8224        | 1.5929 | 900  | 1.0228          |
+| 0.8139        | 1.6814 | 950  | 1.0217          |
+| 0.8032        | 1.7699 | 1000 | 1.0215          |
 ### Framework versions
 - Transformers 4.44.2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7374f96face1008c969763c124bc96b0cfaf866d9ada3bdd3bea82b2f8feb574
 size 538090408

 version https://git-lfs.github.com/spec/v1
+oid sha256:fbf2be0e533bd520d1515ea30a93d5f7f577b5c7e77859d4c7e777f793d56377
 size 538090408

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80414ebaed242bd5e6ac088d04e06fbdf6034a48f5c18884e399c9187ee1a49e
 size 5841

 version https://git-lfs.github.com/spec/v1
+oid sha256:cac94b8fd624a2156b514596933e6443a01788909f285a6ae563166120c04169
 size 5841