Instructions to use wandb/gemma-2b-zephyr-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wandb/gemma-2b-zephyr-sft with Transformers:

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

pipe = pipeline("text-generation", model="wandb/gemma-2b-zephyr-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("wandb/gemma-2b-zephyr-sft")
model = AutoModelForCausalLM.from_pretrained("wandb/gemma-2b-zephyr-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 wandb/gemma-2b-zephyr-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wandb/gemma-2b-zephyr-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": "wandb/gemma-2b-zephyr-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wandb/gemma-2b-zephyr-sft

SGLang

How to use wandb/gemma-2b-zephyr-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 "wandb/gemma-2b-zephyr-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": "wandb/gemma-2b-zephyr-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 "wandb/gemma-2b-zephyr-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": "wandb/gemma-2b-zephyr-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wandb/gemma-2b-zephyr-sft with Docker Model Runner:
```
docker model run hf.co/wandb/gemma-2b-zephyr-sft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Gemma 2B Zephyr SFT

The Zephyr SFT recipe applied on top of Gemma 2B

Model description

Model type: A 2.5B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
Language(s) (NLP): Primarily English
Finetuned from model: google/gemma-7b

Recipe

We trained using the alignment handbook recipe and logging to W&B

Visit the W&B workspace here

License

This model has the same license as the original Gemma model collection

Compute provided by Lambda Labs - 8xA100 80GB node

Around 2 hours to train

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	47.18
AI2 Reasoning Challenge (25-Shot)	49.74
HellaSwag (10-Shot)	72.38
MMLU (5-Shot)	41.37
TruthfulQA (0-shot)	34.42
Winogrande (5-shot)	66.93
GSM8k (5-shot)	18.27