QaiserShumail/gemma-2-qa-finetuned

Model name and description here

Gemma 2 2B-IT Fine-tuned for Question Answering

This model is a fine-tuned version of google/gemma-2-2b-it optimized for question answering tasks.

Model Details

• Base model: google/gemma-2-2b-it
• Fine-tuning method: LoRA (Low-Rank Adaptation)
• BLEU Score: 0.0301
• SacreBLEU Score: 4.4093

Usage

With Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QaiserShumail/gemma-2-qa-finetuned")
model = AutoModelForCausalLM.from_pretrained("QaiserShumail/gemma-2-qa-finetuned")

# Ask a question
question = "Your question here"
prompt = f"<start_of_turn>user\nAnswer this question: {question}<end_of_turn>\n<start_of_turn>model\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
answer = answer.split("<start_of_turn>model\n")[1].split("<end_of_turn>")[0]
print(answer)

With LM Studio

1. Download LM Studio
2. Add this model from Hugging Face Hub
3. Run inference with the prompt format:

   <start_of_turn>user
   Answer this question: Your question here
   <end_of_turn>
   <start_of_turn>model