Instructions to use Fizzarolli/sappha-2b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fizzarolli/sappha-2b-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Fizzarolli/sappha-2b-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fizzarolli/sappha-2b-v1")
model = AutoModelForCausalLM.from_pretrained("Fizzarolli/sappha-2b-v1")
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 Settings

vLLM

How to use Fizzarolli/sappha-2b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fizzarolli/sappha-2b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fizzarolli/sappha-2b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fizzarolli/sappha-2b-v1

SGLang

How to use Fizzarolli/sappha-2b-v1 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 "Fizzarolli/sappha-2b-v1" \
    --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": "Fizzarolli/sappha-2b-v1",
		"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 "Fizzarolli/sappha-2b-v1" \
        --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": "Fizzarolli/sappha-2b-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fizzarolli/sappha-2b-v1 with Docker Model Runner:
```
docker model run hf.co/Fizzarolli/sappha-2b-v1
```

WARNING. THIS SUCKS AND IS PROBABLY VERY BROKEN

please use v3 :)

OLD CONTENT BELOW:

sappha-2b-v1

a very experimental qlora finetune of the gemma-2b base model on various instruct datasets. trained with unsloth.

MIGHT WORK, MIGHT NOT, YOUR MILEAGE MAY VARY

gemma fp16 exports in unsloth seem relatively busted at the moment so beware, this model may not work properly at the moment

prompt

basic chatml format:

<|im_start|>user
What is artificial intelligence?<|im_end|>
<|im_start|>assistant
Artificial intelligence (AI) is a branch of computer science that focuses on creating intelligent machines that can perform tasks that typically require human intelligence.<|im_end|>

quants

ggml: soon™️

datasets used

portions of:

cosmopedia
capybara
airoboros-3.2

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

BF16

Fizzarolli
/

sappha-2b-v1