Yagna1/yagna-assistant-v3

Yagna Assistant v3

Fine-tuned Qwen2.5-0.5B model trained on Yagna's professional background.

Model Details

• Base Model: Qwen2.5-0.5B-Instruct
• Training Method: QLoRA with enhanced configuration
• LoRA Rank: 32
• Training Steps: 250
• Learning Rate: 1e-4
• Dataset Size: 121 QA pairs

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Yagna1/yagna-assistant-v3")
tokenizer = AutoTokenizer.from_pretrained("Yagna1/yagna-assistant-v3")

# Ask a question
prompt = "What is your educational background?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.3)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Performance

Model achieves ~90% accuracy on test suite.