Instructions to use Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit with Transformers:

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

pipe = pipeline("text-generation", model="Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit")
model = AutoModelForCausalLM.from_pretrained("Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit")
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 Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit

SGLang

How to use Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit 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 "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit" \
    --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": "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit",
		"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 "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit" \
        --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": "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit with Docker Model Runner:
```
docker model run hf.co/Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit
```

Bielik-11B-v2.3-Instruct-QuIP-2bit

QuIP# (E8P12 lattice codebook) 2-bit quantization of speakleash/Bielik-11B-v2.3-Instruct.

Model Details

Attribute	Value
Base model	speakleash/Bielik-11B-v2.3-Instruct
Architecture	Mistral (50 layers, 4096 hidden, 32 heads, 8 KV heads)
Quantization method	QuIP# with E8P12 lattice codebook
Precision	2-bit weights (FP16 base)
Model size	3.26 GB (vs ~22 GB FP16, ~6.7x compression)
Calibration	CulturaX-PL (512 samples, 4096 tokens each)

Evaluation (Polish LLM Leaderboard)

Evaluated on 22/23 tasks from the SpeakLeash Open PL LLM Leaderboard (eq_bench excluded due to private dataset).

Metric	Score
Normalized avg (22 tasks)	61.10
FP16 baseline	65.71
Retention	~93% of FP16 quality

Full per-task results: Jakubrd4/bielik-q2-sharp

Comparison with IQ2_XXS (llama.cpp)

Metric	QuIP# E8P12	IQ2_XXS	FP16
Raw avg (22 tasks)	71.92	72.07	75.40
Tasks won (head-to-head)	11/22	11/22	—

QuIP# achieves parity with llama.cpp IQ2_XXS on 22 Polish benchmarks (delta -0.15%).

Usage

Requires quip-sharp for inference:

from lib.utils.unsafe_import import model_from_hf_path

model, tokenizer = model_from_hf_path(
    "Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit"
)

Note: Bielik uses Mistral architecture. QuIP# expects LlamaConfig, so a patch in model_from_hf_path() is needed to convert MistralConfig to LlamaConfig (map sliding_window -> None, attention_dropout -> 0).

Related Resources

Evaluation data & scripts: Jakubrd4/bielik-q2-sharp
Hessian matrices: Jakubrd4/bielik-quip-e8p12 (in hessians/ directory)
Base model: speakleash/Bielik-11B-v2.3-Instruct
QuIP# paper: arXiv:2307.13304

Downloads last month: 1

Safetensors

Model size

0.6B params

Tensor type

I64

F16

Model tree for Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit

Base model

speakleash/Bielik-11B-v2.3-Instruct

Finetuned

(7)

this model

Paper for Jakubrd4/Bielik-11B-v2.3-Instruct-QuIP-2bit

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Paper • 2307.13304 • Published Jul 25, 2023 • 2