Instructions to use adeo/smollm2-135M-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adeo/smollm2-135M-sft with Transformers:

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

pipe = pipeline("text-generation", model="adeo/smollm2-135M-sft")
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("adeo/smollm2-135M-sft")
model = AutoModelForCausalLM.from_pretrained("adeo/smollm2-135M-sft", 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 adeo/smollm2-135M-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adeo/smollm2-135M-sft"
# 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/smollm2-135M-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adeo/smollm2-135M-sft

SGLang

How to use adeo/smollm2-135M-sft 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/smollm2-135M-sft" \
    --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/smollm2-135M-sft",
		"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/smollm2-135M-sft" \
        --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/smollm2-135M-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adeo/smollm2-135M-sft with Docker Model Runner:
```
docker model run hf.co/adeo/smollm2-135M-sft
```

adeo commited on Apr 22, 2025

Commit

4e715bc

verified ·

1 Parent(s): 104dab6

Model save

Browse files

Files changed (12) hide show

README.md +1 -1
all_results.json +6 -6
model.safetensors +1 -1
runs/Apr21_23-18-32_gboye-System-Product-Name/events.out.tfevents.1745296340.gboye-System-Product-Name.22997.0 +3 -0
runs/Apr21_23-59-01_gboye-System-Product-Name/events.out.tfevents.1745297972.gboye-System-Product-Name.23664.0 +3 -0
runs/Apr22_00-00-25_gboye-System-Product-Name/events.out.tfevents.1745298029.gboye-System-Product-Name.24096.0 +3 -0
runs/Apr22_00-01-23_gboye-System-Product-Name/events.out.tfevents.1745298088.gboye-System-Product-Name.24431.0 +3 -0
runs/Apr22_00-02-27_gboye-System-Product-Name/events.out.tfevents.1745298150.gboye-System-Product-Name.24761.0 +3 -0
tokenizer.json +1 -6
train_results.json +6 -6
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/w8gh0yt4)
 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/ugo8ezc5)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.999839180079193,
-    "total_flos": 5.107118882548613e+17,
-    "train_loss": 1.2020252186394083,
-    "train_runtime": 79741.0974,
     "train_samples": 460142,
-    "train_samples_per_second": 11.541,
-    "train_steps_per_second": 0.18
 }

 {
+    "epoch": 1.9999210266535044,
+    "total_flos": 3.966176424708014e+17,
+    "train_loss": 1.3566406987474495,
+    "train_runtime": 18822.9291,
     "train_samples": 460142,
+    "train_samples_per_second": 43.052,
+    "train_steps_per_second": 0.673
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f37e3b35f8623c1aa84a911011064647b1443429762f6667e4b2fb5a5018931
 size 269060552

 version https://git-lfs.github.com/spec/v1
+oid sha256:6fa831a9ab2771b8f61218365619dca935fdbb7a641b830e1a780f373ad9142f
 size 269060552

runs/Apr21_23-18-32_gboye-System-Product-Name/events.out.tfevents.1745296340.gboye-System-Product-Name.22997.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f139286576d004b53b3df8f0fba44a5cf9267de2776c63c6eb21e87b14810f2a
+size 17543

runs/Apr21_23-59-01_gboye-System-Product-Name/events.out.tfevents.1745297972.gboye-System-Product-Name.23664.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff2bda6e25ca690c56e7774015bd53957d7b72f06662a979c27fcc1bc389da9
+size 6034

runs/Apr22_00-00-25_gboye-System-Product-Name/events.out.tfevents.1745298029.gboye-System-Product-Name.24096.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf33dbfb950bb02a6b30009aaec4828ea38bf25e4b78a945cec7845f3d3ae8d
+size 6034

runs/Apr22_00-01-23_gboye-System-Product-Name/events.out.tfevents.1745298088.gboye-System-Product-Name.24431.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6836790173439bbc02d74f4c1bea988b937b3f96019291d58e6f10d23b87bf
+size 6447

runs/Apr22_00-02-27_gboye-System-Product-Name/events.out.tfevents.1745298150.gboye-System-Product-Name.24761.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:500e8461f0c4eb7c609f2b521c5dd03f0c05a21dc976ad4741601334b5fee52b
+size 540875

tokenizer.json CHANGED Viewed

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
   "padding": null,
   "added_tokens": [
     {

 {
   "version": "1.0",
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.999839180079193,
-    "total_flos": 5.107118882548613e+17,
-    "train_loss": 1.2020252186394083,
-    "train_runtime": 79741.0974,
     "train_samples": 460142,
-    "train_samples_per_second": 11.541,
-    "train_steps_per_second": 0.18
 }

 {
+    "epoch": 1.9999210266535044,
+    "total_flos": 3.966176424708014e+17,
+    "train_loss": 1.3566406987474495,
+    "train_runtime": 18822.9291,
     "train_samples": 460142,
+    "train_samples_per_second": 43.052,
+    "train_steps_per_second": 0.673
 }

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 sha256:759445f6712fccd72e2a2299eec62f5fc1dd31f00c61fca92798cbc9f01581b5
 size 6968

 version https://git-lfs.github.com/spec/v1
+oid sha256:85375179406bca01f5322c42059c3c2c3c49d1ad7a2e4eafc59c80426433f699
 size 6968