Instructions to use pranavgupta/gemma4-creole-mt-2026-baseline-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pranavgupta/gemma4-creole-mt-2026-baseline-adapter with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/teamspace/studios/this_studio/gemma-4-E2B") model = PeftModel.from_pretrained(base_model, "pranavgupta/gemma4-creole-mt-2026-baseline-adapter") - Transformers
How to use pranavgupta/gemma4-creole-mt-2026-baseline-adapter with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="pranavgupta/gemma4-creole-mt-2026-baseline-adapter")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pranavgupta/gemma4-creole-mt-2026-baseline-adapter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Gemma-4 E2B β Creole MT Baseline Adapter
LoRA adapter fine-tuned on Kreyol-MT (Robinson et al., NAACL 2024), covering 86 language pairs across 50 Creole and related languages.
Results (dev set, 10 epochs, 8Γ L40S)
| Metric | Base Gemma-4 | + This adapter | Ξ |
|---|---|---|---|
| Macro BLEU | 7.19 | 18.48 | +11.29 |
| Macro chrF | 20.90 | 36.94 | +16.04 |
| Corpus BLEU | 5.57 | 18.48 | +12.91 |
| Corpus chrF | 21.82 | 38.48 | +16.66 |
Training details
- Base model: google/gemma-4-E2B
- Method: LoRA (r=64, Ξ±=128, target=all-linear)
- Training data: Kreyol-MT public split β 86 language pairs, temperature-sampled (T=5, NLLB-style) to 50k examples per epoch
- Epochs: 10
- Precision: bf16
- Hardware: 8Γ NVIDIA L40S
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch
model_id = "google/gemma-4-E2B"
adapter_id = "pranavgupta/gemma4-creole-mt-2026-baseline-adapter"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16).cuda()
model = PeftModel.from_pretrained(model, adapter_id)
model = model.merge_and_unload()
prompt = "Translate this from Haitian Creole into English:\nBonjou, kijan ou rele?\n### Translation:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=100, do_sample=False)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Framework versions
- PEFT 0.19.1
- Downloads last month
- 9
Model tree for pranavgupta/gemma4-creole-mt-2026-baseline-adapter
Base model
google/gemma-4-E2B