Instructions to use Fizzarolli/sappha-2b-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fizzarolli/sappha-2b-v3 with Transformers:

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

pipe = pipeline("text-generation", model="Fizzarolli/sappha-2b-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fizzarolli/sappha-2b-v3")
model = AutoModelForCausalLM.from_pretrained("Fizzarolli/sappha-2b-v3")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Fizzarolli/sappha-2b-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fizzarolli/sappha-2b-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fizzarolli/sappha-2b-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Fizzarolli/sappha-2b-v3

SGLang

How to use Fizzarolli/sappha-2b-v3 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-v3" \
    --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": "Fizzarolli/sappha-2b-v3",
		"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 "Fizzarolli/sappha-2b-v3" \
        --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": "Fizzarolli/sappha-2b-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Fizzarolli/sappha-2b-v3 with Docker Model Runner:
```
docker model run hf.co/Fizzarolli/sappha-2b-v3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

sappha-2b-v3

a slightly less experimental qlora instruct finetune of the gemma-2b base model. trained with unsloth.

benchmarks

	gemma-2b-it	sappha-2b-v3	dolphin-2.8-gemma-2b
MMLU (five-shot)	36.98	38.02	37.89
HellaSwag (zero-shot)	49.22	51.70	47.79
PIQA (one-shot)	75.08	75.46	71.16
TruthfulQA (zero-shot)	37.51	31.65	37.15

prompt format

basic chatml:

<|im_start|>system
You are a useful and helpful AI assistant.<|im_end|>
<|im_start|>user
what are LLMs?<|im_end|>
<|im_start|>assistant
LLMs, or Large Language Models, are advanced artificial intelligence systems that can perform tasks similar to human language. They are trained on vast amounts of data and can understand and respond to human queries. LLMs are often used in various applications, such as language translation, text generation, and question answering.<|im_end|>

quants

gguf: https://huggingface.co/Fizzarolli/sappha-2b-v3-GGUF

what happened to v2?

it was a private failure :)

Downloads last month: 73

Safetensors

Model size

3B params

Tensor type

F32

Model tree for Fizzarolli/sappha-2b-v3

Quantizations

2 models

Fizzarolli
/

sappha-2b-v3