stukenov

ekitil-core-qwen3-600m-kkru-translate-v1

Model Details

Table with columns: Property, Value
Property	Value
Architecture	Qwen3ForCausalLM (decoder-only)
Parameters	673.8M
Base model	ekitil-core-qwen3-600m-kkru-base-v1
Training data	ekitil-parallel-kkru-v2 (5.1M kk-ru pairs)
Training examples	10.2M (both directions: kk->ru + ru->kk)
Training steps	19,921 (~0.5 epochs)
Final loss	2.62
LR	2e-5 (cosine decay, 500 warmup)
Effective batch	256 (32 x 8 grad accum)
Hardware	1x NVIDIA H100 80GB
Training time	~4.5h

Translation Format

markdown
<|kk|> казахский текст <|translate|> <|ru|>  -> generates Russian translation
<|ru|> русский текст <|translate|> <|kk|>    -> generates Kazakh translation

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "stukenov/ekitil-core-qwen3-600m-kkru-translate-v1",
    dtype=torch.bfloat16, device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("stukenov/ekitil-core-qwen3-600m-kkru-translate-v1")

# Kazakh -> Russian
prompt = "<|kk|> Қазақстан — Орталық Азиядағы ең үлкен мемлекет. <|translate|> <|ru|>"
ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, repetition_penalty=1.3, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

# Russian -> Kazakh
prompt = "<|ru|> Образование является ключом к успеху. <|translate|> <|kk|>"
ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, repetition_penalty=1.3, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

Training Data

5.1M deduplicated kk-ru parallel pairs from 13 sources:

Table with columns: Source, Pairs
Source	Pairs
WMT19 crawl	4,512,841
KazParC (human-translated)	362,208
OPUS (12 corpora)	225,924
Total	5,100,973

See ekitil-parallel-kkru-v2 for full details.

Generation Examples

Generated with repetition_penalty=1.3, num_beams=4:

Kazakh -> Russian:

SRC: Қазақстан — Орталық Азиядағы ең үлкен мемлекет.

OUT: Казахстан является одним из крупнейших государств мира.

SRC: Бүгін ауа райы өте жақсы.

OUT: У нас очень хорошая погода.

SRC: Мен университетте оқимын.

OUT: У нас в университете.

Russian -> Kazakh:

SRC: Казахстан — красивая страна с богатой историей.

OUT: Қазақстан — Қазақстанның ең бай тарихы. Қазақстан — өте бай ел.

SRC: Здравствуйте, как у вас дела?

OUT: Сіздер туралы айтып беріңізші.

SRC: Образование является ключом к успеху.

OUT: Өнеркәсiптiк iс-әрекеттiң ерекшелiктерi бiр-бiрiмен байланысты.

Note: Translation captures meaning but quality varies. The model was trained for only 0.5 epochs — more training would improve fluency. Use repetition_penalty >= 1.3 to avoid repetition.

Limitations

Decoder-only architecture may repeat output; use repetition_penalty >= 1.2
Trained for only 0.5 epochs; more training could improve quality
Best for sentence-level translation, not full documents
Translation quality varies by domain (strongest on legal/government text from WMT19)

EkiTil Model Family

Table with columns: Model, Type, Params, HF
Model	Type	Params	HF
EkiTil-123M	Base LM	124.7M	base-v1
EkiTil-300M	Base LM	245.9M	base-v1
EkiTil-600M	Base LM	673.8M

License

MIT

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

stukenov

Model Tree

Base

stukenov/ekitil-core-qwen3-600m-kkru-base-v1

Fine-tuned

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

Model Details

Table with columns: Property, Value
Property	Value
Architecture	Qwen3ForCausalLM (decoder-only)
Parameters	673.8M
Base model	ekitil-core-qwen3-600m-kkru-base-v1
Training data	ekitil-parallel-kkru-v2 (5.1M kk-ru pairs)
Training examples	10.2M (both directions: kk->ru + ru->kk)
Training steps	19,921 (~0.5 epochs)
Final loss	2.62
LR	2e-5 (cosine decay, 500 warmup)
Effective batch	256 (32 x 8 grad accum)
Hardware	1x NVIDIA H100 80GB
Training time	~4.5h

Translation Format

markdown
<|kk|> казахский текст <|translate|> <|ru|>  -> generates Russian translation
<|ru|> русский текст <|translate|> <|kk|>    -> generates Kazakh translation

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "stukenov/ekitil-core-qwen3-600m-kkru-translate-v1",
    dtype=torch.bfloat16, device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("stukenov/ekitil-core-qwen3-600m-kkru-translate-v1")

# Kazakh -> Russian
prompt = "<|kk|> Қазақстан — Орталық Азиядағы ең үлкен мемлекет. <|translate|> <|ru|>"
ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, repetition_penalty=1.3, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

# Russian -> Kazakh
prompt = "<|ru|> Образование является ключом к успеху. <|translate|> <|kk|>"
ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=100, repetition_penalty=1.3, eos_token_id=tokenizer.eos_token_id)
print(tokenizer.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

Training Data

5.1M deduplicated kk-ru parallel pairs from 13 sources:

Table with columns: Source, Pairs
Source	Pairs
WMT19 crawl	4,512,841
KazParC (human-translated)	362,208
OPUS (12 corpora)	225,924
Total	5,100,973

See ekitil-parallel-kkru-v2 for full details.

Generation Examples

Generated with repetition_penalty=1.3, num_beams=4:

Kazakh -> Russian:

SRC: Қазақстан — Орталық Азиядағы ең үлкен мемлекет.

OUT: Казахстан является одним из крупнейших государств мира.

SRC: Бүгін ауа райы өте жақсы.

OUT: У нас очень хорошая погода.

SRC: Мен университетте оқимын.

OUT: У нас в университете.

Russian -> Kazakh:

SRC: Казахстан — красивая страна с богатой историей.

OUT: Қазақстан — Қазақстанның ең бай тарихы. Қазақстан — өте бай ел.

SRC: Здравствуйте, как у вас дела?

OUT: Сіздер туралы айтып беріңізші.

SRC: Образование является ключом к успеху.

OUT: Өнеркәсiптiк iс-әрекеттiң ерекшелiктерi бiр-бiрiмен байланысты.

Note: Translation captures meaning but quality varies. The model was trained for only 0.5 epochs — more training would improve fluency. Use repetition_penalty >= 1.3 to avoid repetition.

Limitations

Decoder-only architecture may repeat output; use repetition_penalty >= 1.2
Trained for only 0.5 epochs; more training could improve quality
Best for sentence-level translation, not full documents
Translation quality varies by domain (strongest on legal/government text from WMT19)

EkiTil Model Family

Table with columns: Model, Type, Params, HF
Model	Type	Params	HF
EkiTil-123M	Base LM	124.7M	base-v1
EkiTil-300M	Base LM	245.9M	base-v1
EkiTil-600M	Base LM	673.8M

License

MIT

ekitil-core-qwen3-600m-kkru-translate-v1

README

Model Details

Translation Format

Usage

Training Data

Generation Examples

Limitations

EkiTil Model Family

License

Explore FriendliAI today

README

Model Details

Translation Format

Usage

Training Data

Generation Examples

Limitations

EkiTil Model Family

License