Instructions to use TilQazyna/Til-2B-GEC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TilQazyna/Til-2B-GEC with Transformers:

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

pipe = pipeline("text-generation", model="TilQazyna/Til-2B-GEC")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TilQazyna/Til-2B-GEC")
model = AutoModelForCausalLM.from_pretrained("TilQazyna/Til-2B-GEC")
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 TilQazyna/Til-2B-GEC with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TilQazyna/Til-2B-GEC

SGLang

How to use TilQazyna/Til-2B-GEC 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 "TilQazyna/Til-2B-GEC" \
    --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": "TilQazyna/Til-2B-GEC",
		"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 "TilQazyna/Til-2B-GEC" \
        --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": "TilQazyna/Til-2B-GEC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TilQazyna/Til-2B-GEC with Docker Model Runner:
```
docker model run hf.co/TilQazyna/Til-2B-GEC
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Til-2B-GEC

Til-2B-GEC — қазақ мәтініндегі грамматикалық, орфографиялық және пунктуациялық қателерді түзететін модель. Til-2B base-моделінің fine-tune нұсқасы.

Til-2B-GEC is a Kazakh grammatical-error-correction model — a fine-tune of the Til-2B base model. Given a Kazakh sentence with spelling, grammar or punctuation errors, it returns a corrected version.

What it fixes

Trained on Kazakh error pairs spanning 10 grammar categories:

Септік жалғау (case endings) · Жіктік жалғау (personal/predicative endings)
Тәуелдік жалғау (possessive) · Көптік жалғау (plural)
Шылау (postpositions/particles) · Шақ (tense) · Болымсыздық (negation)
Сөз тәртібі (word order) · Құрмалас сөйлем (compound sentences) · Үндестік заңы (vowel/consonant harmony)
Kazakh-letter confusions (жанбыр→жаңбыр, бул→бұл, окыдым→оқыдым), capitalization, missing punctuation.

Model details


Base	TilQazyna/Til-2B (1977M, dense + MLA)
Format	ChatML, assistant-only loss
Data	~316K Kazakh GEC pairs: human-annotated grammar errors (10 categories) + synthetic typed-error injection over clean sentences
Epochs / LR	3 / 1e-5 (cosine), bf16
Context	4096

The training instruction (fixed, Kazakh):

Мәтіндегі грамматикалық, орфографиялық және пунктуациялық қателерді түзет. Тек түзетілген мәтінді қайтар.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "TilQazyna/Til-2B-GEC"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto")

INSTR = ("Мәтіндегі грамматикалық, орфографиялық және пунктуациялық қателерді түзет. "
         "Тек түзетілген мәтінді қайтар.")

def correct(text: str) -> str:
    msgs = [{"role": "user", "content": f"{INSTR}\n\nМәтін: {text}"}]
    prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
    ids = tok(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
    out = model.generate(ids, max_new_tokens=128, do_sample=False, pad_token_id=0,
                         eos_token_id=tok.convert_tokens_to_ids("<|im_end|>"))
    text_out = tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True)
    return text_out.strip().split("\n")[0].strip()

print(correct("Алматыда ауа райы жақсы болды кеше жанбыр жауды"))

Intended use & limitations

Intended: correcting single sentences or short paragraphs of Kazakh text.
Best on single sentences; correct long inputs sentence-by-sentence.
May occasionally rephrase rather than minimally correct.
Kazakh only; not a style checker or translator.
No safety alignment has been applied.

License

Apache 2.0. Access is gated (manual approval) for usage tracking.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for TilQazyna/Til-2B-GEC

Base model

TilQazyna/Til-2B

Finetuned

(2)

this model