Text Generation
Transformers
Safetensors
Polish
gpt2
gollem
polish
sft
from-scratch
amd-rocm
Eval Results (legacy)
text-generation-inference
Instructions to use SlayerLab/goLLeM-110M-PL-SFT-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SlayerLab/goLLeM-110M-PL-SFT-merged with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SlayerLab/goLLeM-110M-PL-SFT-merged")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SlayerLab/goLLeM-110M-PL-SFT-merged") model = AutoModelForCausalLM.from_pretrained("SlayerLab/goLLeM-110M-PL-SFT-merged", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SlayerLab/goLLeM-110M-PL-SFT-merged with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SlayerLab/goLLeM-110M-PL-SFT-merged" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SlayerLab/goLLeM-110M-PL-SFT-merged", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SlayerLab/goLLeM-110M-PL-SFT-merged
- SGLang
How to use SlayerLab/goLLeM-110M-PL-SFT-merged 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/goLLeM-110M-PL-SFT-merged" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SlayerLab/goLLeM-110M-PL-SFT-merged", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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/goLLeM-110M-PL-SFT-merged" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SlayerLab/goLLeM-110M-PL-SFT-merged", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SlayerLab/goLLeM-110M-PL-SFT-merged with Docker Model Runner:
docker model run hf.co/SlayerLab/goLLeM-110M-PL-SFT-merged
card: oznaczenie jezyka PL/EN per benchmark (model-index + tabele flagi)
Browse files
README.md
CHANGED
|
@@ -16,41 +16,41 @@ model-index:
|
|
| 16 |
- name: goLLeM-110M-PL-SFT-merged
|
| 17 |
results:
|
| 18 |
- task: {type: text-classification, name: Polish topic classification}
|
| 19 |
-
dataset: {type: sdadas/8tags, name: 8Tags, split: test}
|
| 20 |
metrics:
|
| 21 |
-
- {type: accuracy, value: 0.110247, name: Accuracy}
|
| 22 |
-
- {type: f1, value: 0.034779, name: Macro-F1}
|
| 23 |
- task: {type: text-classification, name: Polish sentiment (in-domain)}
|
| 24 |
-
dataset: {type: allegro/klej-polemo2-in, name: PolEmo2-IN, split: test}
|
| 25 |
metrics:
|
| 26 |
-
- {type: accuracy, value: 0.423823, name: Accuracy}
|
| 27 |
-
- {type: f1, value: 0.242625, name: Macro-F1}
|
| 28 |
- task: {type: text-classification, name: Polish sentiment (out-of-domain)}
|
| 29 |
-
dataset: {type: allegro/klej-polemo2-out, name: PolEmo2-OUT, split: test}
|
| 30 |
metrics:
|
| 31 |
-
- {type: accuracy, value: 0.356275, name: Accuracy}
|
| 32 |
-
- {type: f1, value: 0.169887, name: Macro-F1}
|
| 33 |
-
- task: {type: text-generation, name:
|
| 34 |
-
dataset: {type: blimp, name: BLiMP, split: train}
|
| 35 |
-
metrics: [{type: acc, value: 0.5404}]
|
| 36 |
-
- task: {type: text-generation, name:
|
| 37 |
-
dataset: {type: EleutherAI/lambada_openai, name: LAMBADA OpenAI, split: test}
|
| 38 |
-
metrics: [{type: acc, value: 0.0223}, {type: perplexity, value: 55056.11}]
|
| 39 |
-
- task: {type: text-generation, name:
|
| 40 |
-
dataset: {type: hellaswag, name: HellaSwag, split: validation}
|
| 41 |
-
metrics: [{type: acc_norm, value: 0.2817}]
|
| 42 |
-
- task: {type: text-generation, name:
|
| 43 |
-
dataset: {type: piqa, name: PIQA, split: validation}
|
| 44 |
-
metrics: [{type: acc_norm, value: 0.5065}]
|
| 45 |
-
- task: {type: text-generation, name:
|
| 46 |
-
dataset: {type: sciq, name: SciQ, split: test}
|
| 47 |
-
metrics: [{type: acc_norm, value: 0.6000}]
|
| 48 |
-
- task: {type: text-generation, name:
|
| 49 |
-
dataset: {type: allenai/ai2_arc, config: ARC-Easy, name: ARC-Easy, split: test}
|
| 50 |
-
metrics: [{type: acc_norm, value: 0.2597}]
|
| 51 |
-
- task: {type: text-generation, name:
|
| 52 |
-
dataset: {type: allenai/ai2_arc, config: ARC-Challenge, name: ARC-Challenge, split: test}
|
| 53 |
-
metrics: [{type: acc_norm, value: 0.2270}]
|
| 54 |
---
|
| 55 |
|
| 56 |
# GoLLeM-110M-PL-SFT-merged
|
|
@@ -73,35 +73,35 @@ Instruction-tuned (SFT) wersja **GoLLeM-110M-PL** — małego, polskojęzycznego
|
|
| 73 |
|
| 74 |
## Baza, dane i trening
|
| 75 |
|
| 76 |
-
- **Model bazowy:** [SlayerLab/goLLeM-110M-PL](https://huggingface.co/SlayerLab/goLLeM-110M-PL) (ckpt_00060733), pretrenowany od zera na korpusie **dynaword-expansion** (HPLT v3.0 `pol_Latn`, ~1,35 mld tokenów, 1 epoka), PII-scrubbed.
|
| 77 |
- **SFT:** grounded-QA, **26 194 par** (4 autorów, CC-BY-SA-inherit); 3 epoki, lr 2e-5, weight decay 0.1, batch 16 × accum 4 (efektywny 64), ~3 min 40 s na RX 7900 XTX (ROCm).
|
| 78 |
- **Gate treningowy:** PII 0, regurgitacja 0 (model składa ze wzorców, nie recytuje danych); forma odpowiedzi 15/15 (0 kontynuacji, 0 boilerplate).
|
| 79 |
|
| 80 |
## Ewaluacja
|
| 81 |
|
| 82 |
-
Zero-shot, pełne splity. **Bateria EN:** `lm-evaluation-harness` 0.4.12 (te same taski i wersja co karta [Pollock](https://huggingface.co/SlayerLab/pollock-mini-lm-125m)). **Bateria PL:** port protokołu dmpod (`eval_pl_bench`, mean-loglikelihood-per-token, length-normalized, accuracy + macro-F1). Pomiar: SlayerLab (Latarnik/Hart), 2026-08-27, RX 7900 XTX.
|
| 83 |
|
| 84 |
-
|
| 85 |
|
| 86 |
-
| Benchmark | Accuracy | Macro-F1 | Próbki |
|
| 87 |
-
|---|---:|---:|---:|
|
| 88 |
-
| 8Tags | 0.1102 | 0.0348 | 4 372 |
|
| 89 |
-
| PolEmo2-IN | 0.4238 | 0.2426 | 722 |
|
| 90 |
-
| PolEmo2-OUT | 0.3563 | 0.1699 | 494 |
|
| 91 |
|
| 92 |
-
|
| 93 |
|
| 94 |
-
| Benchmark | Metryka | Wynik |
|
| 95 |
-
|---|---|---:|
|
| 96 |
-
| BLiMP | acc | 0.5404 |
|
| 97 |
-
| LAMBADA OpenAI | acc | 0.0223 (ppl 55056) |
|
| 98 |
-
| HellaSwag | acc_norm | 0.2817 |
|
| 99 |
-
| PIQA | acc_norm | 0.5065 |
|
| 100 |
-
| SciQ | acc_norm | 0.6000 |
|
| 101 |
-
| ARC-Easy | acc_norm | 0.2597 |
|
| 102 |
-
| ARC-Challenge | acc_norm | 0.2270 |
|
| 103 |
|
| 104 |
-
**Interpretacja (uczciwie):** to model **polski**.
|
| 105 |
|
| 106 |
## Użycie
|
| 107 |
|
|
@@ -122,7 +122,7 @@ print(tok.decode(out[0], skip_special_tokens=True))
|
|
| 122 |
## Ograniczenia i odpowiedzialne użycie
|
| 123 |
|
| 124 |
- Mały model (110M) — generuje **pewnie brzmiące nieprawdy** i potrafi dryfować z tematu; wiedza faktograficzna jest ograniczona skalą.
|
| 125 |
-
- Trenowany i oceniany głównie po polsku; po angielsku ~losowo.
|
| 126 |
- Kontekst 512 tokenów, brak filtrów bezpieczeństwa na wyjściu.
|
| 127 |
- **PII:** może generować prawdopodobnie brzmiące imiona/adresy = **konfabulacje**, nie dane realnych osób; kontaktowe PII (telefon/e-mail/PESEL) było scrubowane w korpusie (model zwraca tagi `[Telefon]`/`[PII]`). Weryfikacja wyjścia po stronie użytkownika.
|
| 128 |
|
|
|
|
| 16 |
- name: goLLeM-110M-PL-SFT-merged
|
| 17 |
results:
|
| 18 |
- task: {type: text-classification, name: Polish topic classification}
|
| 19 |
+
dataset: {type: sdadas/8tags, name: 8Tags (Polish), split: test}
|
| 20 |
metrics:
|
| 21 |
+
- {type: accuracy, value: 0.110247, name: Accuracy (PL)}
|
| 22 |
+
- {type: f1, value: 0.034779, name: Macro-F1 (PL)}
|
| 23 |
- task: {type: text-classification, name: Polish sentiment (in-domain)}
|
| 24 |
+
dataset: {type: allegro/klej-polemo2-in, name: PolEmo2-IN (Polish), split: test}
|
| 25 |
metrics:
|
| 26 |
+
- {type: accuracy, value: 0.423823, name: Accuracy (PL)}
|
| 27 |
+
- {type: f1, value: 0.242625, name: Macro-F1 (PL)}
|
| 28 |
- task: {type: text-classification, name: Polish sentiment (out-of-domain)}
|
| 29 |
+
dataset: {type: allegro/klej-polemo2-out, name: PolEmo2-OUT (Polish), split: test}
|
| 30 |
metrics:
|
| 31 |
+
- {type: accuracy, value: 0.356275, name: Accuracy (PL)}
|
| 32 |
+
- {type: f1, value: 0.169887, name: Macro-F1 (PL)}
|
| 33 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 34 |
+
dataset: {type: blimp, name: BLiMP (English), split: train}
|
| 35 |
+
metrics: [{type: acc, value: 0.5404, name: acc (EN)}]
|
| 36 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 37 |
+
dataset: {type: EleutherAI/lambada_openai, name: LAMBADA OpenAI (English), split: test}
|
| 38 |
+
metrics: [{type: acc, value: 0.0223, name: acc (EN)}, {type: perplexity, value: 55056.11, name: perplexity (EN)}]
|
| 39 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 40 |
+
dataset: {type: hellaswag, name: HellaSwag (English), split: validation}
|
| 41 |
+
metrics: [{type: acc_norm, value: 0.2817, name: acc_norm (EN)}]
|
| 42 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 43 |
+
dataset: {type: piqa, name: PIQA (English), split: validation}
|
| 44 |
+
metrics: [{type: acc_norm, value: 0.5065, name: acc_norm (EN)}]
|
| 45 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 46 |
+
dataset: {type: sciq, name: SciQ (English), split: test}
|
| 47 |
+
metrics: [{type: acc_norm, value: 0.6000, name: acc_norm (EN)}]
|
| 48 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 49 |
+
dataset: {type: allenai/ai2_arc, config: ARC-Easy, name: ARC-Easy (English), split: test}
|
| 50 |
+
metrics: [{type: acc_norm, value: 0.2597, name: acc_norm (EN)}]
|
| 51 |
+
- task: {type: text-generation, name: English zero-shot (cross-lingual transfer)}
|
| 52 |
+
dataset: {type: allenai/ai2_arc, config: ARC-Challenge, name: ARC-Challenge (English), split: test}
|
| 53 |
+
metrics: [{type: acc_norm, value: 0.2270, name: acc_norm (EN)}]
|
| 54 |
---
|
| 55 |
|
| 56 |
# GoLLeM-110M-PL-SFT-merged
|
|
|
|
| 73 |
|
| 74 |
## Baza, dane i trening
|
| 75 |
|
| 76 |
+
- **Model bazowy:** [SlayerLab/goLLeM-110M-PL](https://huggingface.co/SlayerLab/goLLeM-110M-PL) (ckpt_00060733), pretrenowany od zera na korpusie **dynaword-expansion** (HPLT v3.0 `pol_Latn`, ~1,35 mld tokenów, 1 epoka), PII-scrubbed. **Język treningu: 100% polski.**
|
| 77 |
- **SFT:** grounded-QA, **26 194 par** (4 autorów, CC-BY-SA-inherit); 3 epoki, lr 2e-5, weight decay 0.1, batch 16 × accum 4 (efektywny 64), ~3 min 40 s na RX 7900 XTX (ROCm).
|
| 78 |
- **Gate treningowy:** PII 0, regurgitacja 0 (model składa ze wzorców, nie recytuje danych); forma odpowiedzi 15/15 (0 kontynuacji, 0 boilerplate).
|
| 79 |
|
| 80 |
## Ewaluacja
|
| 81 |
|
| 82 |
+
Zero-shot, pełne splity. Ewaluacja pokrywa **dwa języki**: **polski (3 benchmarki)** — realna kompetencja modelu — oraz **angielski (7 benchmarków)** — transfer międzyjęzykowy (model jest jednojęzyczny polski, więc EN mierzy transfer, nie zdolność). **Bateria EN:** `lm-evaluation-harness` 0.4.12 (te same taski i wersja co karta [Pollock](https://huggingface.co/SlayerLab/pollock-mini-lm-125m)). **Bateria PL:** port protokołu dmpod (`eval_pl_bench`, mean-loglikelihood-per-token, length-normalized, accuracy + macro-F1). Pomiar: SlayerLab (Latarnik/Hart), 2026-08-27, RX 7900 XTX.
|
| 83 |
|
| 84 |
+
### 🇵🇱 Bateria POLSKA — kompetencja (random: 8Tags .125, PolEmo2 .25)
|
| 85 |
|
| 86 |
+
| Benchmark | Język | Accuracy | Macro-F1 | Próbki |
|
| 87 |
+
|---|:---:|---:|---:|---:|
|
| 88 |
+
| 8Tags | 🇵🇱 PL | 0.1102 | 0.0348 | 4 372 |
|
| 89 |
+
| PolEmo2-IN | 🇵🇱 PL | 0.4238 | 0.2426 | 722 |
|
| 90 |
+
| PolEmo2-OUT | 🇵🇱 PL | 0.3563 | 0.1699 | 494 |
|
| 91 |
|
| 92 |
+
### 🇬🇧 Bateria ANGIELSKA — transfer międzyjęzykowy (random: BLiMP/PIQA .5, reszta ~.25)
|
| 93 |
|
| 94 |
+
| Benchmark | Język | Metryka | Wynik |
|
| 95 |
+
|---|:---:|---|---:|
|
| 96 |
+
| BLiMP | 🇬🇧 EN | acc | 0.5404 |
|
| 97 |
+
| LAMBADA OpenAI | 🇬🇧 EN | acc | 0.0223 (ppl 55056) |
|
| 98 |
+
| HellaSwag | 🇬🇧 EN | acc_norm | 0.2817 |
|
| 99 |
+
| PIQA | 🇬🇧 EN | acc_norm | 0.5065 |
|
| 100 |
+
| SciQ | 🇬🇧 EN | acc_norm | 0.6000 |
|
| 101 |
+
| ARC-Easy | 🇬🇧 EN | acc_norm | 0.2597 |
|
| 102 |
+
| ARC-Challenge | 🇬🇧 EN | acc_norm | 0.2270 |
|
| 103 |
|
| 104 |
+
**Interpretacja (uczciwie):** to model **polski** (trenowany 100% PL). Bateria 🇵🇱 mierzy realną kompetencję, bateria 🇬🇧 — transfer międzyjęzykowy. Na EN wypada ~losowo (LAMBADA ppl 55056 = nie przewiduje angielskiego następnego słowa) — to oczekiwane dla modelu monolingwalnego, nie wada. Sygnał jest tam, gdzie powinien: PolEmo2-IN 0.424 (nad losowym 0.25). Uwaga porównawcza: względem bazy GoLLeM-110M-PL SFT nie podniósł zdolności zero-shot klasyfikacji (8Tags pozostaje ~losowo; wzrost accuracy PolEmo2 idzie w parze ze spadkiem macro-F1 = przesunięcie ku klasie większościowej). Model najlepiej traktować jako **completion/instruction-following bazowej skali**, nie jako klasyfikator. Confound porównań z modelami innej klasy: różny słownik i długość kontekstu.
|
| 105 |
|
| 106 |
## Użycie
|
| 107 |
|
|
|
|
| 122 |
## Ograniczenia i odpowiedzialne użycie
|
| 123 |
|
| 124 |
- Mały model (110M) — generuje **pewnie brzmiące nieprawdy** i potrafi dryfować z tematu; wiedza faktograficzna jest ograniczona skalą.
|
| 125 |
+
- Trenowany i oceniany głównie po polsku; po angielsku ~losowo (transfer).
|
| 126 |
- Kontekst 512 tokenów, brak filtrów bezpieczeństwa na wyjściu.
|
| 127 |
- **PII:** może generować prawdopodobnie brzmiące imiona/adresy = **konfabulacje**, nie dane realnych osób; kontaktowe PII (telefon/e-mail/PESEL) było scrubowane w korpusie (model zwraca tagi `[Telefon]`/`[PII]`). Weryfikacja wyjścia po stronie użytkownika.
|
| 128 |
|