Instructions to use SystemAdmin123/SmolLM-360M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SystemAdmin123/SmolLM-360M with Transformers:

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

pipe = pipeline("text-generation", model="SystemAdmin123/SmolLM-360M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SystemAdmin123/SmolLM-360M")
model = AutoModelForCausalLM.from_pretrained("SystemAdmin123/SmolLM-360M", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SystemAdmin123/SmolLM-360M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SystemAdmin123/SmolLM-360M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SystemAdmin123/SmolLM-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SystemAdmin123/SmolLM-360M

SGLang

How to use SystemAdmin123/SmolLM-360M 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 "SystemAdmin123/SmolLM-360M" \
    --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": "SystemAdmin123/SmolLM-360M",
		"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 "SystemAdmin123/SmolLM-360M" \
        --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": "SystemAdmin123/SmolLM-360M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SystemAdmin123/SmolLM-360M with Docker Model Runner:
```
docker model run hf.co/SystemAdmin123/SmolLM-360M
```

SystemAdmin123 commited on Feb 1, 2025

Commit

7210ab5

verified ·

1 Parent(s): 932f804

Training in progress, step 40, checkpoint

Browse files

Files changed (4) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/trainer_state.json +17 -17
last-checkpoint/training_args.bin +1 -1

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fd01a8bae891e64aa1a626cc333858550e0cb6e36fcb7777c30999ee762d5e
 size 723674912

 version https://git-lfs.github.com/spec/v1
+oid sha256:ea2ad4c7c610b5e4ef126bc494685c8d4930ad390366ab2e84a4faeb7d420766
 size 723674912

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbf48b20262fa5e0455f8bf8dec46b89425e9f2d27bcf272b7ece12dbc3f48cb
 size 735625370

 version https://git-lfs.github.com/spec/v1
+oid sha256:6c39f051c45f03d6dcadc277c1454a36b0adc05bc85d9ce17d6a180588b3cad4
 size 735625370

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -11,53 +11,53 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 2.6000850200653076,
-      "eval_runtime": 5.1412,
-      "eval_samples_per_second": 292.148,
-      "eval_steps_per_second": 18.284,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
-      "grad_norm": 4.21875,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.4519,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
       "grad_norm": 1.15625,
       "learning_rate": 3.2000000000000005e-05,
-      "loss": 2.4462,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
-      "eval_loss": 2.592799425125122,
-      "eval_runtime": 5.3446,
-      "eval_samples_per_second": 281.033,
-      "eval_steps_per_second": 17.588,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
-      "grad_norm": 3.9375,
       "learning_rate": 4.8e-05,
-      "loss": 2.5891,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
       "grad_norm": 1.5,
       "learning_rate": 6.400000000000001e-05,
-      "loss": 2.4169,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
-      "eval_loss": 2.5311338901519775,
-      "eval_runtime": 5.3509,
-      "eval_samples_per_second": 280.702,
-      "eval_steps_per_second": 17.567,
       "step": 40
     }
   ],

     {
       "epoch": 0.001183431952662722,
       "eval_loss": 2.6000850200653076,
+      "eval_runtime": 4.9168,
+      "eval_samples_per_second": 305.481,
+      "eval_steps_per_second": 19.118,
       "step": 1
     },
     {
       "epoch": 0.011834319526627219,
+      "grad_norm": 4.3125,
       "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4524,
       "step": 10
     },
     {
       "epoch": 0.023668639053254437,
       "grad_norm": 1.15625,
       "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.4454,
       "step": 20
     },
     {
       "epoch": 0.023668639053254437,
+      "eval_loss": 2.5929689407348633,
+      "eval_runtime": 5.1638,
+      "eval_samples_per_second": 290.869,
+      "eval_steps_per_second": 18.204,
       "step": 20
     },
     {
       "epoch": 0.03550295857988166,
+      "grad_norm": 4.0,
       "learning_rate": 4.8e-05,
+      "loss": 2.5904,
       "step": 30
     },
     {
       "epoch": 0.047337278106508875,
       "grad_norm": 1.5,
       "learning_rate": 6.400000000000001e-05,
+      "loss": 2.4156,
       "step": 40
     },
     {
       "epoch": 0.047337278106508875,
+      "eval_loss": 2.5310535430908203,
+      "eval_runtime": 5.1508,
+      "eval_samples_per_second": 291.604,
+      "eval_steps_per_second": 18.249,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56abc2533c0578396c842febb0d8251535aeccfdad6e84eb864bab834fbe822f
 size 6712

 version https://git-lfs.github.com/spec/v1
+oid sha256:f671da996f9974e01b0bb6a782a1b157ff77bf2c5559d84c73598d7fc8d1f978
 size 6712