Instructions to use adeo/smollm-360M-instruct-new with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adeo/smollm-360M-instruct-new with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adeo/smollm-360M-instruct-new")
model = AutoModelForCausalLM.from_pretrained("adeo/smollm-360M-instruct-new")
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 adeo/smollm-360M-instruct-new with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adeo/smollm-360M-instruct-new

SGLang

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

Docker Model Runner
How to use adeo/smollm-360M-instruct-new with Docker Model Runner:
```
docker model run hf.co/adeo/smollm-360M-instruct-new
```

adeo commited on Apr 4, 2025

Commit

9bd71aa

verified ·

1 Parent(s): 1328e35

Model save

Browse files

Files changed (7) hide show

README.md +1 -1
all_results.json +5 -5
model.safetensors +1 -1
runs/Apr04_14-15-40_73046ea093b0/events.out.tfevents.1743776165.73046ea093b0.7387.0 +3 -0
train_results.json +5 -5
trainer_state.json +0 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/7e64o2gq)
 This model was trained with SFT.

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/3v8yzei2)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9999235532451648,
-    "total_flos": 1.024299027881001e+17,
-    "train_loss": 1.1466178722155569,
-    "train_runtime": 11966.5261,
     "train_samples": 321330,
-    "train_samples_per_second": 8.745,
-    "train_steps_per_second": 0.547
 }

 {
     "epoch": 0.9999235532451648,
+    "total_flos": 1.1949402256048128e+17,
+    "train_loss": 1.1248935338554031,
+    "train_runtime": 10312.3192,
     "train_samples": 321330,
+    "train_samples_per_second": 10.148,
+    "train_steps_per_second": 0.159
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f8564cd6476d6de51763addb9989e6bf6d3ca18bc585f60f942c6d5b112dcd
 size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:9ce6830c2ce8b95fcc2be5a6701c195e6d63a04cc766f535004f226d03f44706
 size 269060552

runs/Apr04_14-15-40_73046ea093b0/events.out.tfevents.1743776165.73046ea093b0.7387.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:594a1239efdbb8ae370e0d62d91f33659c320bf7abfd1b5236e0d55f3d5d3f28
+size 75364

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9999235532451648,
-    "total_flos": 1.024299027881001e+17,
-    "train_loss": 1.1466178722155569,
-    "train_runtime": 11966.5261,
     "train_samples": 321330,
-    "train_samples_per_second": 8.745,
-    "train_steps_per_second": 0.547
 }

 {
     "epoch": 0.9999235532451648,
+    "total_flos": 1.1949402256048128e+17,
+    "train_loss": 1.1248935338554031,
+    "train_runtime": 10312.3192,
     "train_samples": 321330,
+    "train_samples_per_second": 10.148,
+    "train_steps_per_second": 0.159
 }

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0753b93833f9b20b3f3f27dc9e29aa04c0bdbc87262daff1d48a2ac02fcb21
 size 7032

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ea3491f097db4782571c8d4818c36289ee9ec6d2c3d910679835821d9f79fb5
 size 7032