Luganda-gemma-1B-it

Luganda

Translation

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch

base_model_id = "google/gemma-3-1b-it"
adapter_id = "AmplifiedAccess/Luganda-gemma-1b-it"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)

model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.bfloat16,
    ),
    device_map={"": 0},
)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

# Translate civic content English → Luganda
prompt = "Translate to Luganda:\nA community officer can help residents complete forms, check eligibility, and even process applications offline."
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", return_dict=True, add_generation_prompt=True
).to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)

prompt_len = inputs["input_ids"].shape[1]
response = tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True).strip()
print(response)

Swahili-gemma-1B-it

Swahili

Translation

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "AmplifiedAccess/Swahili-gemma-1b-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.float16, device_map="auto")

prompt = ("<start_of_turn>user\n"
          "Translate the following English sentence to Swahili.\n"
          "English: The children are playing outside.\nSwahili:<end_of_turn>\n"
          "<start_of_turn>model\n")

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)

response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response.strip())

Swahili-nllb-1.3B

Swahili

Translation

import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

base_model_id = "facebook/nllb-200-distilled-1.3B"
adapter_id = "AmplifiedAccess/Swahili-nllb-1.3b"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

text = "A community officer can help residents complete forms, check eligibility, and even process applications offline."
inputs = tokenizer(text, return_tensors="pt")
target_lang_id = tokenizer.convert_tokens_to_ids("swh_Latn")

with torch.no_grad():
    outputs = model.generate(**inputs, forced_bos_token_id=target_lang_id, max_new_tokens=128)

print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])

Swahili-nllb-600M

Swahili

Translation

import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

base_model_id = "facebook/nllb-200-distilled-600M"
adapter_id = "AmplifiedAccess/Swahili-nllb-600m"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

text = "A community officer can help residents complete forms, check eligibility, and even process applications offline."
inputs = tokenizer(text, return_tensors="pt")
target_lang_id = tokenizer.convert_tokens_to_ids("swh_Latn")

with torch.no_grad():
    outputs = model.generate(**inputs, forced_bos_token_id=target_lang_id, max_new_tokens=128)

print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])

Luganda-gemma-1B-it

Luganda

Translation

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel
import torch

base_model_id = "google/gemma-3-1b-it"
adapter_id = "AmplifiedAccess/Luganda-gemma-1b-it"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)

model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.bfloat16,
    ),
    device_map={"": 0},
)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

# Translate civic content English → Luganda
prompt = "Translate to Luganda:\nA community officer can help residents complete forms, check eligibility, and even process applications offline."
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(
    messages, return_tensors="pt", return_dict=True, add_generation_prompt=True
).to(model.device)

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)

prompt_len = inputs["input_ids"].shape[1]
response = tokenizer.decode(outputs[0][prompt_len:], skip_special_tokens=True).strip()
print(response)

Swahili-gemma-1B-it

Swahili

Translation

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "AmplifiedAccess/Swahili-gemma-1b-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.float16, device_map="auto")

prompt = ("<start_of_turn>user\n"
          "Translate the following English sentence to Swahili.\n"
          "English: The children are playing outside.\nSwahili:<end_of_turn>\n"
          "<start_of_turn>model\n")

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)

response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response.strip())

Swahili-nllb-1.3B

Swahili

Translation

import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

base_model_id = "facebook/nllb-200-distilled-1.3B"
adapter_id = "AmplifiedAccess/Swahili-nllb-1.3b"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

text = "A community officer can help residents complete forms, check eligibility, and even process applications offline."
inputs = tokenizer(text, return_tensors="pt")
target_lang_id = tokenizer.convert_tokens_to_ids("swh_Latn")

with torch.no_grad():
    outputs = model.generate(**inputs, forced_bos_token_id=target_lang_id, max_new_tokens=128)

print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])

Swahili-nllb-600M

Swahili

Translation

import torch
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

base_model_id = "facebook/nllb-200-distilled-600M"
adapter_id = "AmplifiedAccess/Swahili-nllb-600m"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, src_lang="eng_Latn")
model = AutoModelForSeq2SeqLM.from_pretrained(base_model_id)
model = PeftModel.from_pretrained(model, adapter_id)
model.eval()

text = "A community officer can help residents complete forms, check eligibility, and even process applications offline."
inputs = tokenizer(text, return_tensors="pt")
target_lang_id = tokenizer.convert_tokens_to_ids("swh_Latn")

with torch.no_grad():
    outputs = model.generate(**inputs, forced_bos_token_id=target_lang_id, max_new_tokens=128)

print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])