Instructions to use speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit with Transformers:

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

pipe = pipeline("text-generation", model="speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit")
model = AutoModelForCausalLM.from_pretrained("speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit")
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 speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit

SGLang

How to use speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit 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 "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit" \
    --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": "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit",
		"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 "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit" \
        --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": "speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit with Docker Model Runner:
```
docker model run hf.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit
```

Bielik-11B-v2.2-Instruct-Quanto-8bit

This model was converted to Quanto format from SpeakLeash's Bielik-11B-v.2.2-Instruct.

DISCLAIMER: Be aware that quantised models show reduced response quality and possible hallucinations!

About Quanto

Optimum Quanto is a pytorch quantization backend for optimum. Model can be loaded using:

from optimum.quanto import QuantizedModelForCausalLM

qmodel = QuantizedModelForCausalLM.from_pretrained('speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit')

Model description:

Developed by: SpeakLeash & ACK Cyfronet AGH
Language: Polish
Model type: causal decoder-only
Quant from: Bielik-11B-v2.2-Instruct
Finetuned from: Bielik-11B-v2
License: Apache 2.0 and Terms of Use

Responsible for model quantization

Remigiusz Kinas^SpeakLeash - team leadership, conceptualizing, calibration data preparation, process creation and quantized model delivery.

Contact Us

If you have any questions or suggestions, please use the discussion tab. If you want to contact us directly, join our Discord SpeakLeash.

Downloads last month: 188

Safetensors

Model size

11B params

Tensor type

F32

Model tree for speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit

Base model

speakleash/Bielik-11B-v2

Finetuned

speakleash/Bielik-11B-v2.2-Instruct

Finetuned

(9)

this model

Collection including speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit

Bielik-11B-v2.2

Collection

A collection of models based on Bielik-11B-v2.2 - instruct and quantized versions. • 17 items • Updated Mar 19 • 28