Instructions to use Nondzu/zephyr-7b-beta-pl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nondzu/zephyr-7b-beta-pl with Transformers:

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

pipe = pipeline("text-generation", model="Nondzu/zephyr-7b-beta-pl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nondzu/zephyr-7b-beta-pl")
model = AutoModelForCausalLM.from_pretrained("Nondzu/zephyr-7b-beta-pl")
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 Nondzu/zephyr-7b-beta-pl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nondzu/zephyr-7b-beta-pl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nondzu/zephyr-7b-beta-pl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nondzu/zephyr-7b-beta-pl

SGLang

How to use Nondzu/zephyr-7b-beta-pl 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 "Nondzu/zephyr-7b-beta-pl" \
    --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": "Nondzu/zephyr-7b-beta-pl",
		"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 "Nondzu/zephyr-7b-beta-pl" \
        --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": "Nondzu/zephyr-7b-beta-pl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nondzu/zephyr-7b-beta-pl with Docker Model Runner:
```
docker model run hf.co/Nondzu/zephyr-7b-beta-pl
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Overview

The model is a result of advanced fine-tuning methods applied to a base model, focusing on enhancing its capabilities for specific Polish language datasets. It incorporates cutting-edge techniques and is built upon the Zephyr Beta model framework.

Current Status: Alpha

Stage: Alpha-Alpaca

Training Details

I trained the model using 3xRTX 3090 for 163 hours.

Quantised Model Links:

Model Specifics

Base Model: HuggingFaceH4/zephyr-7b-beta
Fine-Tuning Method: QLORA
Primary Focus: Polish language datasets

Datasets:

Dataset 1 Name: Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
Dataset 1 Link: Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
Dataset 2 Name: klima7/polish-prose
Dataset 2 Link: klima7/polish-prose

Usage Warning

As this is an experimental model, users should be aware of the following:

Reliability: The model has not been fully tested and may exhibit unexpected behaviors or performance issues.
Updates: The model is subject to change based on ongoing testing and feedback.
Data Sensitivity: Users should exercise caution when using sensitive or private data, as the model's output and behavior are not fully predictable at this stage.

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Example

Feedback and Contribution

User feedback is crucial during this testing phase. We encourage users to provide feedback on model performance, issues encountered, and any suggestions for improvements. Contributions in terms of shared test results, datasets, or code improvements are also welcome.

Disclaimer: This experimental model is provided 'as is', without warranty of any kind. Users should use the model at their own risk. The creators or maintainers of the model are not responsible for any consequences arising from its use.

Downloads last month: 10

Safetensors

Model size

7B params

Tensor type

F16

Model tree for Nondzu/zephyr-7b-beta-pl

Quantizations

3 models