πŸ€– Enterprise FAQ Conversational Assistant (Fine-Tuned Adapter)

Lightweight Contextual Q&A and FAQ Resolution

Developed by Vipplav AI β€” India's Most Specialized AI Studio

Website GitHub License


πŸ“Œ Model Overview

Vipplav/gemma-finetuned-faq is a LoRA adapter fine-tuned on top of TinyLlama/TinyLlama-1.1B-Chat-v1.0 optimized for enterprise conversational FAQ and knowledge retrieval.

  • Base Model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
  • Fine-Tuning Method: LoRA (Rank-adapted attention projections on q_proj & v_proj)
  • Primary Use Case: Enterprise customer support, automated knowledge-base replies, low-latency chatbot backend (<100ms on GPU, sub-second on modern CPU).

πŸš€ Quickstart Inference

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

base_model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
adapter_id = "Vipplav/gemma-finetuned-faq"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()

prompt = "<|system|>\nYou are an enterprise support AI.</s>\n<|user|>\nWhat is the SLA for enterprise support inquiries?</s>\n<|assistant|>\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.2)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

🏒 About Vipplav AI

Vipplav AI is an enterprise AI studio engineering foundational Indic Small Language Models (Rachana) and verifiable agentic automation pipelines.

Downloads last month
21
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Vipplav/gemma-finetuned-faq

Adapter
(1,614)
this model