Instructions to use TilQazyna/Til-mini-1B-GEC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TilQazyna/Til-mini-1B-GEC with Transformers:

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

pipe = pipeline("text-generation", model="TilQazyna/Til-mini-1B-GEC")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TilQazyna/Til-mini-1B-GEC")
model = AutoModelForCausalLM.from_pretrained("TilQazyna/Til-mini-1B-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-mini-1B-GEC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TilQazyna/Til-mini-1B-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-mini-1B-GEC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TilQazyna/Til-mini-1B-GEC

SGLang

How to use TilQazyna/Til-mini-1B-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-mini-1B-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-mini-1B-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-mini-1B-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-mini-1B-GEC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TilQazyna/Til-mini-1B-GEC with Docker Model Runner:
```
docker model run hf.co/TilQazyna/Til-mini-1B-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-mini-1B-GEC

Til-mini-1B-GEC — қазақ мәтініндегі грамматикалық, орфографиялық және пунктуациялық қателерді түзететін модель. Til-mini-1B base-моделінің жеңіл fine-tune нұсқасы.

Til-mini-1B-GEC is a Kazakh grammatical-error-correction model: a light instruction fine-tune of the Til-mini-1B base model. Given a Kazakh sentence with spelling, grammar or punctuation errors, it returns a corrected version.

What it fixes

Kazakh-specific letter confusions: жанбыр → жаңбыр, кызыкты → қызық(ты), окыдым → оқыдым, бул → бұл
Capitalization at sentence start
Missing end-of-sentence punctuation
Common agreement/spelling slips in informal text

Model details


Base	TilQazyna/Til-mini-1B (956.3M, dense + MLA)
Fine-tune format	ChatML (`<
Loss	assistant tokens only
Data	Kazakh GEC pairs: organic social-media sentences + synthetic errors (~900 pairs)
Epochs / LR	5 / 1e-5 (cosine), bf16
Context	2048

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-mini-1B-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)
    # The model may continue after the corrected sentence — keep the first line/sentence.
    return text_out.strip().split("\n")[0].strip()

print(correct("Алматыда ауа райы жақсы болды кеше жанбыр жауды"))
# → Алматыда ауа райы жақсы болды кеше жаңбыр жауды.

Real examples (greedy decoding):

Input	Output (first sentence)
`мен мектепке барамын деп айтты ол кеше`	`Мен мектепке барамын деп айтты ол кеше.`
`Алматыда ауа райы жақсы болды кеше жанбыр жауды`	`Алматыда ауа райы жақсы болды кеше жаңбыр жауды.`
`бул кітап өте кызыкты екен мен оны окыдым`	`Кітап өте қызық екен мен оны оқыдым.`

Intended use & limitations

Intended: correcting single sentences or short paragraphs of informal Kazakh text.
Stopping: the fine-tune corpus is small (~900 pairs), so the model does not always emit <|im_end|> reliably and may repeat the corrected sentence — always post-process to the first line/sentence as in the snippet above. Long multi-sentence inputs are best corrected sentence-by-sentence.
The model may occasionally rephrase rather than minimally correct.
Not a style checker and not a translator; Kazakh only.
No safety alignment has been applied.

License

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

Downloads last month: -

Safetensors

Model size

1.0B params

Tensor type

BF16

Model tree for TilQazyna/Til-mini-1B-GEC

Base model

TilQazyna/Til-mini-1B

Finetuned

(1)

this model