Instructions to use DrRiceIO7/SmolLM2-1.7B-SFT-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DrRiceIO7/SmolLM2-1.7B-SFT-Merged with Transformers:

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

pipe = pipeline("text-generation", model="DrRiceIO7/SmolLM2-1.7B-SFT-Merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DrRiceIO7/SmolLM2-1.7B-SFT-Merged")
model = AutoModelForCausalLM.from_pretrained("DrRiceIO7/SmolLM2-1.7B-SFT-Merged")
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 DrRiceIO7/SmolLM2-1.7B-SFT-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DrRiceIO7/SmolLM2-1.7B-SFT-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DrRiceIO7/SmolLM2-1.7B-SFT-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DrRiceIO7/SmolLM2-1.7B-SFT-Merged

SGLang

How to use DrRiceIO7/SmolLM2-1.7B-SFT-Merged 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 "DrRiceIO7/SmolLM2-1.7B-SFT-Merged" \
    --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": "DrRiceIO7/SmolLM2-1.7B-SFT-Merged",
		"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 "DrRiceIO7/SmolLM2-1.7B-SFT-Merged" \
        --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": "DrRiceIO7/SmolLM2-1.7B-SFT-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use DrRiceIO7/SmolLM2-1.7B-SFT-Merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DrRiceIO7/SmolLM2-1.7B-SFT-Merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DrRiceIO7/SmolLM2-1.7B-SFT-Merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DrRiceIO7/SmolLM2-1.7B-SFT-Merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DrRiceIO7/SmolLM2-1.7B-SFT-Merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use DrRiceIO7/SmolLM2-1.7B-SFT-Merged with Docker Model Runner:
```
docker model run hf.co/DrRiceIO7/SmolLM2-1.7B-SFT-Merged
```

Hi! I'm back. School has been a b- and a half and I've been really out of it because of the weather, but I'm back. This is my next attempt at doing CPT and SFT on a model. It's not good, but I think I'm making progress. Also, if you saw this when it first came out, no you didn't. I had that one going overnight and the grad_norm had apparently climbed into the few hundred thousands, so it was bascially stuck for over half the run. This one is still bad, but not as bad. Everyone feel free to tweak this to make this better. Please let me know how you do it and how well it goes!