Instructions to use patrickfleith/smollm3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use patrickfleith/smollm3-sft with Transformers:

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

pipe = pipeline("text-generation", model="patrickfleith/smollm3-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("patrickfleith/smollm3-sft")
model = AutoModelForCausalLM.from_pretrained("patrickfleith/smollm3-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use patrickfleith/smollm3-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "patrickfleith/smollm3-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickfleith/smollm3-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/patrickfleith/smollm3-sft

SGLang

How to use patrickfleith/smollm3-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 "patrickfleith/smollm3-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickfleith/smollm3-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "patrickfleith/smollm3-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "patrickfleith/smollm3-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use patrickfleith/smollm3-sft with Docker Model Runner:
```
docker model run hf.co/patrickfleith/smollm3-sft
```

patrickfleith commited on Oct 3, 2025

Commit

bd2b195

verified ·

1 Parent(s): a446cd5

Training in progress, step 1000

Browse files

Files changed (3) hide show

model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e161dd78ad883babedf97f0a390a2b1236ff4a04067a4b444e71b8494ecf4f96
 size 4932711224

 version https://git-lfs.github.com/spec/v1
+oid sha256:98b0d14cdd74deba9d25b741528cb52ec40c1b71dbf9bbcd875b470f1d0b85b9
 size 4932711224

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2fccdbf43185820f57e600cdd75771ddbd4bd3942be30d739677a544be9e9c
 size 4999889128

 version https://git-lfs.github.com/spec/v1
+oid sha256:f5b225e3e190f27271fee0f24a762f9262da098d82d2f8ed64f3a57ba7950b71
 size 4999889128

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c94a7ed4f3dbb8278a34df64738cd1169685c930410281abae5b53bb2a751f
 size 2367831672

 version https://git-lfs.github.com/spec/v1
+oid sha256:01718d0de584107e9eb5e6ba8f9ae83ebc4272ec707037cff5532dea7e975b69
 size 2367831672