Instructions to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with Transformers:

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

pipe = pipeline("text-generation", model="SlayerLab/bielik-4.5b-v3-matura-history-sft2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SlayerLab/bielik-4.5b-v3-matura-history-sft2")
model = AutoModelForCausalLM.from_pretrained("SlayerLab/bielik-4.5b-v3-matura-history-sft2", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
# Run inference directly in the terminal:
llama cli -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
# Run inference directly in the terminal:
llama cli -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

Use Docker

docker model run hf.co/SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

LM Studio
Jan

vLLM

How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SlayerLab/bielik-4.5b-v3-matura-history-sft2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SlayerLab/bielik-4.5b-v3-matura-history-sft2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

SGLang

How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 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 "SlayerLab/bielik-4.5b-v3-matura-history-sft2" \
    --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": "SlayerLab/bielik-4.5b-v3-matura-history-sft2",
		"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 "SlayerLab/bielik-4.5b-v3-matura-history-sft2" \
        --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": "SlayerLab/bielik-4.5b-v3-matura-history-sft2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with Ollama:
```
ollama run hf.co/SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
```
Unsloth Desktop
Docker Model Runner
How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with Docker Model Runner:
```
docker model run hf.co/SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M
```

Lemonade

How to use SlayerLab/bielik-4.5b-v3-matura-history-sft2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ2_M

Run and chat with the model

lemonade run user.bielik-4.5b-v3-matura-history-sft2-IQ2_M

List all available models

lemonade list

Atomic Chat

Bielik-4.5B-v3 · matura-history SFT v2 ("Mały, ale wariat")

Full-parameter SFT of speakleash/Bielik-4.5B-v3.0-Instruct on synthetic tasks and model essays in the format of the Polish extended-level history matura (CKE). Built for the "Mały, ale wariat" track of the SlayerLab hackathon: the smallest model file that scores at least 35% on the team's history-matura evaluator. Same recipe and the same 4,144 training rows as the 1.5B sibling, SlayerLab/bielik-1.5b-v3-matura-history-sft2.

Registered candidate: sft45-IQ3_XXS.gguf, 1,851,896,576 bytes (1.85 GB). It is the smallest file that passes both the team evaluator (harness v5) and an unseen CKE May 2026 paper (with and without the harness). The untouched base at the same 3-bit size fails the past-exam track (18/55); the SFT is what brings it to 22/55.

This repo holds the bf16 safetensors (Transformers format, 2 shards), the llama.cpp GGUF quants made with a Polish importance matrix, the imatrix itself, and the training logs. Code, data recipe and every evaluation run: slayerlabs/hackathon → maly-ale-wariat/ (MODEL_CARD.md, RESULTS.md, REPORT.md).

Files

File	Bytes	Notes	sha256
`model-00001-of-00002.safetensors`	4,975,516,024	bf16, Transformers format (+ `config.json`, tokenizer, `chat_template.jinja`, index)	`fc70b9a7e415164087bfd8f2f25189de35cfdfa41574d2d2a7e48cfc88704edb`
`model-00002-of-00002.safetensors`	4,539,113,296		`52a8fd2d1ff17f2e427aa8e448fbeab84ec9bbd9955b74d48dbb01dabbe428a9`
`sft45-bf16.gguf`	9,519,301,024	`convert_hf_to_gguf.py`; the source of every quant below	`5f02a3207d9e29d80ac5596100352afaef9419b6cb88268f259c6140e07bb08a`
`sft45-IQ4_XS.gguf`	2,558,825,216	Best scores in this repo	`d5df84995ddfd912129e85b0b1eb14b6848ab3b9db959fca43a5c64147e357bc`
`sft45-Q3_K_M.gguf`	2,303,443,712	Not evaluated	`fe8ff71654f302eea1a40e0e135519f0d7c9142e255e2121082821cae21aeb8d`
`sft45-IQ3_XXS.gguf`	1,851,896,576	Registered candidate	`9e3254c4e6cf95d4f07a5d3f6ed239dc9c4182ae7a4e49858edc18c7ac19d1f4`
`sft45-IQ2_M.gguf`	1,615,532,800	Fails the past-exam track	`b4cd6325e2f1e76ba473097ca50806c8329f4aa60710e76d6b6fd429181c13e6`
`sft45.imatrix.gguf`	5,655,680	Polish importance matrix: SFT conversations + plwiki passages (`train/make_calib.py`, `calib-v1.txt`)	`73fb9b8faf420a6fee7e791482ac040ce4d26b79fbc7a48df18ac8f9e6815f49`
`training/`		`train_args.json`, `metrics.json`, `log.jsonl`, `data_stats.json`, `gpu.txt`, `out-pip-freeze.txt`
`SHA256SUMS`		sha256 of every file in this repo (`sha256sum -c SHA256SUMS`)

Quants were made with llama.cpp build 11146 (commit 7fe450e19) via train/quantize.sh, with the same Polish calibration text as the 1.5B (calib-v1.txt).

How to run

The configuration that was scored (llama.cpp llama-server, OpenAI-compatible API on port 8891):

hf download SlayerLab/bielik-4.5b-v3-matura-history-sft2 sft45-IQ3_XXS.gguf --local-dir .
llama-server -m sft45-IQ3_XXS.gguf --port 8891 --ctx-size 8192 -ngl 99 --flash-attn on --jinja \
  --chat-template-kwargs '{"enable_thinking":false}'

llama-server -hf SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ3_XXS and ollama run hf.co/SlayerLab/bielik-4.5b-v3-matura-history-sft2:IQ3_XXS also work.

The reported harness scores used matura-harness in front of that server with the flags in maly-ale-wariat/eval/harness_args_v5.txt (evaluator-style prompts for source-based tasks, plwiki BM25 retrieval of 2 × 700 characters only for tasks of 600 characters or less and for essays, strict closed-answer normalization, repetition trimming, DRY sampling and a 380-word floor for essays). The 1.7 GB retrieval index is not part of the model; the steps to rebuild it are in the repo README.

Transformers (bf16 safetensors):

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "SlayerLab/bielik-4.5b-v3-matura-history-sft2"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto")

messages = [
    {"role": "system", "content": "Jesteś zdającym maturę rozszerzoną z historii. Odpowiadasz po polsku, zwięźle i konkretnie. "
                                  "Najważniejsze są źródła podane w zadaniu; materiały pomocnicze mogą być nietrafne. "
                                  "Wykonaj dokładnie polecenie i podaj wymaganą liczbę elementów."},
    {"role": "user", "content": "Podaj nazwę bitwy z 1410 r., w której wojska polsko-litewskie pokonały zakon krzyżacki, "
                                "i wymień jednego z dowódców strony polsko-litewskiej."},
]
ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=200, do_sample=False)
print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))

The system prompt above is the one used in training. Chat template: Bielik ChatML (<s><|im_start|>role\n…<|im_end|>), no thinking mode. Context: 32768 tokens (the scored runs used 8192).

Evaluation

Team evaluator history-matura-eval: two tracks of 55 points each, 34 items adapted from the CKE May 2023 extended-level history paper ("past exam") and 34 Wikipedia-based items, graded by a deterministic closed-answer scorer plus an LLM judge (google/gemini-3.1-flash-lite). Pass = at least 20/55 (35%) on each track. Two protocols:

raw: the evaluator's bare-model runner (its system prompt, the task text only, the answer submitted verbatim);
harness v5: matura-harness with eval/harness_args_v5.txt, as described above.

A third, truly unseen paper, CKE May 2026 (39 items, 60 points, pass = 21), was converted to the evaluator's item format and scored with the same scorer and judge. Scores below are strict re-scores (eval/strict_rescore.py); the value the evaluator reported is in brackets where it differs.

GGUF	Size	Protocol	Past exam (/55)	Wikipedia (/55)	CKE May 2026 (/60)
`sft45-IQ3_XXS`	1.85 GB	harness v5	22 ✅	34 ✅	23 ✅
`sft45-IQ3_XXS`	1.85 GB	raw	incomplete¹	34 ✅	22 ✅
`sft45-IQ4_XS`	2.56 GB	harness v5	25 (27) ✅	37 ✅	23 ✅
`sft45-IQ4_XS`	2.56 GB	raw	–	–	24 ✅
`sft45-IQ2_M`	1.62 GB	harness v5	14 ✗	24 ✅	–
`sft45-IQ2_M`	1.62 GB	raw	12 ✗	21 ✅	–
base `Bielik-4.5B-v3.0-Instruct` Q8_0	5.06 GB	harness v5	41 ✅	38 ✅	38 ✅
base `Bielik-4.5B-v3.0-Instruct` Q8_0	5.06 GB	raw	28 ✅	40 ✅	–
base `Bielik-4.5B-v3-Instruct` i1-IQ3_XXS²	1.85 GB	harness v5	18 ✗	35 ✅	–

¹ The evaluator reports no total when the judge errs or grades an item "review". ² mradermacher's imatrix quant of the ungated mirror, used as the size-matched untouched baseline.

What this shows: the untouched 4.5B has real margin at Q8 (5 GB) but loses most of it below 4 bits (18/55 at IQ3_XXS). The SFT recovers the past-exam track at that size (22/55) and holds 22–23/60 on the unseen 2026 paper, where every 1.5B variant sits at 19–21. The price is a file twice the size of the 1.5B candidate.

Caveats

A single evaluator run varies by about ±3 points; the judge is an LLM. The 22/55 past-exam pass has a 2-point margin.
The bare-runner past-exam score for IQ3_XXS is unavailable (judge error voided the track), so "passes under both protocols" rests on the Wikipedia track and the 2026 paper for the bare protocol.
IQ2_M fails; Q3_K_M was not evaluated.
Known failure modes: true/false statements near chance level, open answers naming the wrong person/place/date, essays with factual errors.

Training


Base	`speakleash/Bielik-4.5B-v3.0-Instruct` (Apache-2.0), loaded from the ungated mirror `adamo1139/Bielik-4.5B-v3-Instruct-ungated`. Both safetensors shards match the LFS sha256 of the gated original (`bae33275…`, `e66d692a…`), so the base is verified identical.
Method	Full-parameter SFT (`train/sft.py`, plain `transformers` 4.57.1), loss only on assistant tokens. Same script and data as the 1.5B.
Data	4,144 chat rows (`sft/v2`, prompt version `compact-v2`) + 116 validation rows: 2,714 synthetic syllabus tasks, 300 model essays (×2), 800 supplementary items, and 82 items converted from the CKE May 2024/2025 papers (×2; not redistributed, CKE copyright). 66% compact prompt with 0–2 retrieved plwiki passages, 20% evaluator-style bare prompt. 2.80M training tokens, 576k of them supervised.
Hyper-parameters	2 epochs, lr 1e-5 cosine to 0.1×, warmup 3%, weight decay 0, batch 4 × grad-accum 8 (effective 32), max length 4096, bf16, gradient checkpointing, seed 42.
Compute	1 × NVIDIA A100 80GB PCIe (RunPod), 260 steps, 1,798 s (30 min).
Loss	train 1.147, eval 1.155 (final; curves in `training/log.jsonl`).

Data provenance and licensing

Weights: Apache-2.0, same as the base model.
The synthetic tasks and essays were written by Claude (Anthropic) via Claude Code workflows following data/gen/STYLE.md, fact-checked by a second agent pass and validated by data/gen/validate_items.py. They are CC BY-SA 4.0-compatible.
Retrieved evidence comes from Polish Wikipedia (CirrusSearch dump 2026-09-20, CC BY-SA 4.0); every record keeps its source URL.
The CKE 2024/2025 items are not redistributed (CKE copyright). The evaluator's questions and keys were never used for training; build_sft.py drops any record sharing word 8-grams with them, plus essays on the held-out themes.

Intended use and limitations

A hackathon research artifact: a small Polish model that answers exam-style history questions in the CKE matura format. It hallucinates names, dates and places, answers true/false items near chance, and was tuned for a specific evaluator. Do not rely on it for factual information or grading.

Acknowledgements

SpeakLeash for Bielik-4.5B-v3.0-Instruct; llama.cpp for quantization and inference; Polish Wikipedia authors (CC BY-SA 4.0).

Downloads last month: 2,120

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for SlayerLab/bielik-4.5b-v3-matura-history-sft2

Base model

speakleash/Bielik-4.5B-v3

Finetuned

speakleash/Bielik-4.5B-v3.0-Instruct

Finetuned

(10)

this model