Text Generation
PEFT
Safetensors
English
tinyllama
lora
faq
conversational-ai
enterprise-ai
vipplav-ai
conversational
Instructions to use Vipplav/gemma-finetuned-faq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Vipplav/gemma-finetuned-faq with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "Vipplav/gemma-finetuned-faq") - Notebooks
- Google Colab
- Kaggle
π€ 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
π 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).
π 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))
π’ About Vipplav AI
Vipplav AI is an enterprise AI studio engineering foundational Indic Small Language Models (Rachana) and verifiable agentic automation pipelines.
- Website: https://www.vipplavai.com
- GitHub: https://github.com/vipplavai
- Contact: hello@vipplavai.com
- Downloads last month
- 21
Model tree for Vipplav/gemma-finetuned-faq
Base model
TinyLlama/TinyLlama-1.1B-Chat-v1.0