This is a Gemma-3-4B instruction-tuned model fine-tuned to handle customer service conversations for a Nigerian bank. The fine-tuning data reflects Nigerian customer-service interactions, so the model's responses are tuned to Nigerian tone and phrasing patterns as they appear in text (e.g. common Nigerian English expressions and code-switching seen in chat/support transcripts). It was trained with Unsloth and Hugging Face's TRL library using parameter-efficient (LoRA) fine-tuning.

Training Details


Base model	unsloth/gemma-3-4b-it-unsloth-bnb-4bit (Gemma 3, 4B, 4-bit quantized)
Method	Supervised fine-tuning with LoRA (via Unsloth + Hugging Face TRL)
LoRA rank (r)	8
LoRA alpha	8
LoRA dropout	0
Target modules	Attention projections (`q_proj`, `k_proj`, `v_proj`, `o_proj`) and MLP projections (`gate_proj`, `up_proj`, `down_proj`) of the language model
Task type	Causal LM
Precision	float16

This repository hosts the full fine-tuned model weights (merged, fp16, split across two safetensors shards) as well as the standalone LoRA adapter (adapter_model.safetensors) used to produce them, so the adapter can also be applied on top of the base model directly if preferred.

Training data, dataset size, and number of training steps/epochs are not recorded in this repository's metadata and are not published here.

Intended Use

Financial services customer support conversations
Loan application assistance and status inquiries
Chat-based customer interaction with Nigerian tone and accent patterns in text

This model is intended as a domain-specific assistant for Nigerian banking customer service scenarios rather than as a general-purpose chat model.

How to Use

The repository contains the full merged model, so it can be loaded directly with transformers (no separate adapter step required):

python

import torch
from transformers import AutoProcessor, Gemma3ForConditionalGeneration

model_id = "Ephraimmm/customer-service"

model = Gemma3ForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16,
)
processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {"role": "user", "content": [{"type": "text", "text": "Good day, please I want to check on my loan application status."}]}
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    output_ids = model.generate(**inputs, max_new_tokens=256)

response = processor.decode(
    output_ids[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True
)
print(response)

Alternatively, load with Unsloth for faster inference:

python

from unsloth import FastModel

model, tokenizer = FastModel.from_pretrained(
    model_name="Ephraimmm/customer-service",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastModel.for_inference(model)

If you only want the LoRA weights, adapter_config.json / adapter_model.safetensors in this repo can be loaded on top of the base model unsloth/gemma-3-4b-it-unsloth-bnb-4bit with peft.

Limitations

This is a domain-specific model tuned for a narrow use case (Nigerian bank customer service, loan-related queries); it has not been evaluated against standard NLP/LLM benchmarks.
No formal evaluation metrics, accuracy figures, or benchmark scores are published for this model — do not assume performance figures not stated here.
As with any fine-tuned LLM, outputs should be reviewed before use in a production financial-services context, particularly for compliance-sensitive communication.
The base architecture (Gemma 3) supports multimodal (image+text) input, but this fine-tune was produced for text-based customer service interaction.

Author

Developed by Ephraimmm

This gemma3 model was trained 2x faster with Unsloth and Hugging Face's TRL library.