GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
gateremark
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
gateremark
Model Tree
google/translategemma-12b-it
Input Modalities
Output Modalities
Supported Functionality
| 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, AutoModelForCausalLMimport 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() # Exampleprint(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 | 0 |
| Learning rate | 2e-4 |
| Batch size | 64 (16 × 4 accum) |
| Epochs | 2 |
| Optimizer | AdamW 8-bit |
| NEFTune α | 5 |
| Weight decay | 0.01 |
python
["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]| 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}}}from transformers import AutoTokenizer, AutoModelForCausalLMimport 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() # Exampleprint(translate_to_kikuyu("Hello, how are you?"))# Output: Hihi, ũrĩ atĩa?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)["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]@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}}}