Instructions to use eryk-mazus/polka-1.1b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eryk-mazus/polka-1.1b-chat with Transformers:

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

pipe = pipeline("text-generation", model="eryk-mazus/polka-1.1b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eryk-mazus/polka-1.1b-chat")
model = AutoModelForCausalLM.from_pretrained("eryk-mazus/polka-1.1b-chat")
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 eryk-mazus/polka-1.1b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eryk-mazus/polka-1.1b-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eryk-mazus/polka-1.1b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eryk-mazus/polka-1.1b-chat

SGLang

How to use eryk-mazus/polka-1.1b-chat 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 "eryk-mazus/polka-1.1b-chat" \
    --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": "eryk-mazus/polka-1.1b-chat",
		"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 "eryk-mazus/polka-1.1b-chat" \
        --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": "eryk-mazus/polka-1.1b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eryk-mazus/polka-1.1b-chat with Docker Model Runner:
```
docker model run hf.co/eryk-mazus/polka-1.1b-chat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Polka-1.1B-Chat

eryk-mazus/polka-1.1b-chat is the first polish model trained to act as a helpful, conversational assistant that can be run locally.

The model is based on TinyLlama-1.1B with the custom, extended tokenizer for more efficient Polish text generation, that was additionally pretrained on 5.7 billion tokens. It was then fine-tuned on around 60k synthetically generated and machine-translated multi-turn conversations with the Direct Preference Optimization (DPO) performed on top of it.

Context size: 4,096 tokens

In addition, we're releasing:

polka-1.1b - our base model with an extended tokenizer and additional pre-training on Polish corpus sampled using DSIR
polka-pretrain-en-pl-v1 - the pre-training dataset
polka-dpo-v1 - dataset of DPO pairs
polka-1.1b-chat-gguf - GGUF files for the chat model

Usage

Sample code:

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer

model_name = "eryk-mazus/polka-1.1b-chat"

tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,
    device_map="auto"
)
streamer = TextStreamer(tokenizer, skip_prompt=True)

# You are a helpful assistant.
system_prompt = "Jesteś pomocnym asystentem."
chat = [{"role": "system", "content": system_prompt}]

# Compose a short song on programming.
user_input = "Napisz krótką piosenkę o programowaniu."
chat.append({"role": "user", "content": user_input})

# Generate - add_generation_prompt to make sure it continues as assistant
inputs = tokenizer.apply_chat_template(chat, add_generation_prompt=True, return_tensors="pt")
# For multi-GPU, find the device of the first parameter of the model
first_param_device = next(model.parameters()).device
inputs = inputs.to(first_param_device)

with torch.no_grad():
    outputs = model.generate(
        inputs,
        pad_token_id=tokenizer.eos_token_id,
        max_new_tokens=512,
        temperature=0.2,
        repetition_penalty=1.15,
        top_p=0.95,
        do_sample=True,
        streamer=streamer,
    )

# Add just the new tokens to our chat
new_tokens = outputs[0, inputs.size(1):]
response = tokenizer.decode(new_tokens, skip_special_tokens=True)
chat.append({"role": "assistant", "content": response})

The model works seamlessly with vLLM as well.

Prompt format

This model uses ChatML as the prompt format:

<|im_start|>system
Jesteś pomocnym asystentem.
<|im_start|>user
Jakie jest dzienne zapotrzebowanie kaloryczne dorosłej osoby?<|im_end|>
<|im_start|>assistant
Dla dorosłych osób zaleca się spożywanie około 2000-3000 kcal dziennie, aby utrzymać optymalne zdrowie i dobre samopoczucie.<|im_end|>

This prompt is available as a chat template, which means you can format messages using the tokenizer.apply_chat_template() method, as demonstrated in the example above.