Instructions to use SultanR/SmolTulu-1.7b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SultanR/SmolTulu-1.7b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SultanR/SmolTulu-1.7b-Instruct")
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("SultanR/SmolTulu-1.7b-Instruct")
model = AutoModelForCausalLM.from_pretrained("SultanR/SmolTulu-1.7b-Instruct", 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 SultanR/SmolTulu-1.7b-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SultanR/SmolTulu-1.7b-Instruct

SGLang

How to use SultanR/SmolTulu-1.7b-Instruct 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 "SultanR/SmolTulu-1.7b-Instruct" \
    --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": "SultanR/SmolTulu-1.7b-Instruct",
		"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 "SultanR/SmolTulu-1.7b-Instruct" \
        --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": "SultanR/SmolTulu-1.7b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SultanR/SmolTulu-1.7b-Instruct with Docker Model Runner:
```
docker model run hf.co/SultanR/SmolTulu-1.7b-Instruct
```

SultanR commited on Dec 17, 2024

Commit

038ba8a

verified ·

1 Parent(s): e29498c

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -0

README.md CHANGED Viewed

@@ -140,6 +140,21 @@ I ran these evaluations using [SmolLM2's evaluation code](https://github.com/hug
 | MMLU-Pro (MCF) | 17.4 | 17.3 | 19.3 | 12.7 | **24.2** | 11.7 |
 | PIQA | 72.2 | 72.1 | **74.4** | 72.3 | 73.2 | 71.6 |
 ## Usage
 Just like any Huggingface model, just run it using the transformers library:

 | MMLU-Pro (MCF) | 17.4 | 17.3 | 19.3 | 12.7 | **24.2** | 11.7 |
 | PIQA | 72.2 | 72.1 | **74.4** | 72.3 | 73.2 | 71.6 |
+## Training Details
+The model was trained using Direct Preference Optimization (DPO) with the following configuration:
+- Base model: SmolLM2-1.7B with AllenAI's SFT pipeline ran
+- Mixed precision: bfloat16
+- Learning rate: 8e-7 with linear scheduler
+- Warmup ratio: 0.1
+- Training epochs: 1
+- Effective batch size: 12
+- Sequence length: 4096 tokens
+- DPO loss: Length-normalized DPO
+- DPO beta: 5.0
+- Gradient checkpointing enabled
+- DeepSpeed Stage 3 for memory optimization
 ## Usage
 Just like any Huggingface model, just run it using the transformers library: