kikuyu_translategemma_12b_merged_V2 API & Inference Endpoint

Model Details

Table with columns: Attribute, Value
Attribute	Value
Base Model	google/translategemma-12b-it
Parameters	12.4B
Fine-tuning Method	LoRA (r=128, alpha=256)
Training Data	30,430 English-Kikuyu pairs
BLEU Score	19.61
Framework	Unsloth + TRL

Usage

Quick Start

python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "gateremark/kikuyu_translategemma_12b_merged_V2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

def translate_to_kikuyu(text: str) -> str:
    messages = [
        {
            "role": "user",
            "content": [{
                "type": "text",
                "source_lang_code": "en",
                "target_lang_code": "ki",
                "text": text
            }]
        }
    ]
    
    input_ids = tokenizer.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_tensors="pt"
    ).to(model.device)
    
    terminators = [
        tokenizer.eos_token_id,
        tokenizer.convert_tokens_to_ids("<end_of_turn>"),
    ]
    
    with torch.no_grad():
        outputs = model.generate(
            input_ids=input_ids,
            max_new_tokens=256,
            temperature=0.3,
            do_sample=True,
            eos_token_id=terminators,
        )
    
    response = tokenizer.decode(
        outputs[0][input_ids.shape[1]:],
        skip_special_tokens=True
    )
    return response.strip()

# Example
print(translate_to_kikuyu("Hello, how are you?"))
# Output: Hihi, ũrĩ atĩa?

Using with Unsloth (Faster Inference)

python
from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="gateremark/kikuyu_translategemma_12b_merged_V2",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,  # Optional: reduce VRAM to ~6GB
)

Training Details

Dataset

Source: gateremark/english-kikuyu-translations
Size: 30,430 parallel sentences
Split: 95% train (28,908) / 5% eval (1,522)

Hyperparameters

Table with columns: Parameter, Value
Parameter	Value
LoRA rank (r)	128
LoRA alpha	256
LoRA dropout	0
Learning rate	2e-4
Batch size	64 (16 × 4 accum)
Epochs	2
Optimizer	AdamW 8-bit
NEFTune α	5
Weight decay	0.01

Target Modules

python
["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]

Hardware

GPU: NVIDIA H200 (139GB VRAM)
Platform: Lightning.ai
Training Time: ~90 minutes

Evaluation

Table with columns: Metric, Score
Metric	Score
BLEU	19.61
Eval Loss	0.578

Sample Translations

Table with columns: English, Kikuyu
English	Kikuyu
Hello, how are you?	Hihi, ũrĩ atĩa?
The weather is beautiful today.	Rĩera nĩ rĩega mũno ũmũthĩ
I love learning new languages.	Nĩ ngenagĩra gũthoma thiomi njerũ

Limitations

Direction: English → Kikuyu only (reverse not trained)
Domain: General text; may struggle with technical/specialized content
Dialects: Trained on standard Kikuyu; dialect variations not covered
Evaluation: BLEU-based; human evaluation in progress

Intended Use

Translation tools for Kikuyu speakers
Language learning applications
Research on low-resource African language NLP
Cultural preservation initiatives

Citation

bibtex
@misc{gatere2026kikuyutranslategemma,
  author = {Mark Gatere},
  title = {Kikuyu TranslateGemma-12B: Fine-tuning TranslateGemma for Low-Resource Bantu Language Translation},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/gateremark/kikuyu_translategemma_12b_merged_V2}}
}

Acknowledgments

Google for the TranslateGemma base model
Unsloth for 2x faster fine-tuning
Lightning.ai for GPU compute

Attribute

Value

Base Model

google/translategemma-12b-it

Parameters

12.4B

Fine-tuning Method

LoRA (r=128, alpha=256)

Training Data

30,430 English-Kikuyu pairs

BLEU Score

19.61

Framework

Unsloth + TRL

python

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "gateremark/kikuyu_translategemma_12b_merged_V2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

def translate_to_kikuyu(text: str) -> str:
    messages = [
        {
            "role": "user",
            "content": [{
                "type": "text",
                "source_lang_code": "en",
                "target_lang_code": "ki",
                "text": text
            }]
        }
    ]
    
    input_ids = tokenizer.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_tensors="pt"
    ).to(model.device)
    
    terminators = [
        tokenizer.eos_token_id,
        tokenizer.convert_tokens_to_ids("<end_of_turn>"),
    ]
    
    with torch.no_grad():
        outputs = model.generate(
            input_ids=input_ids,
            max_new_tokens=256,
            temperature=0.3,
            do_sample=True,
            eos_token_id=terminators,
        )
    
    response = tokenizer.decode(
        outputs[0][input_ids.shape[1]:],
        skip_special_tokens=True
    )
    return response.strip()

# Example
print(translate_to_kikuyu("Hello, how are you?"))
# Output: Hihi, ũrĩ atĩa?

python

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="gateremark/kikuyu_translategemma_12b_merged_V2",
    max_seq_length=2048,
    dtype=None,
    load_in_4bit=True,  # Optional: reduce VRAM to ~6GB
)

Parameter

Value

LoRA rank (r)

128

LoRA alpha

256

LoRA dropout

Learning rate

2e-4

Batch size

64 (16 × 4 accum)

Epochs

Optimizer

AdamW 8-bit

NEFTune α

Weight decay

0.01

Metric

Score

BLEU

19.61

Eval Loss

0.578

English

Kikuyu

Hello, how are you?

Hihi, ũrĩ atĩa?

The weather is beautiful today.

Rĩera nĩ rĩega mũno ũmũthĩ

I love learning new languages.

Nĩ ngenagĩra gũthoma thiomi njerũ

bibtex

@misc{gatere2026kikuyutranslategemma,
  author = {Mark Gatere},
  title = {Kikuyu TranslateGemma-12B: Fine-tuning TranslateGemma for Low-Resource Bantu Language Translation},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/gateremark/kikuyu_translategemma_12b_merged_V2}}
}

kikuyu_translategemma_12b_merged_V2

README

Model Details

Usage

Quick Start

Using with Unsloth (Faster Inference)

Training Details

Dataset

Hyperparameters

Target Modules

Hardware

Evaluation

Sample Translations

Limitations

Intended Use

Citation

Acknowledgments

Explore FriendliAI today

README

Model Details

Usage

Quick Start

Using with Unsloth (Faster Inference)

Training Details

Dataset

Hyperparameters

Target Modules

Hardware

Evaluation

Sample Translations

Limitations

Intended Use

Citation

Acknowledgments